Hacker News Reader

Comment by marcus_holmes | Hacker News Reader

I think this is a great example of both points of view in the ongoing debate.

Pro-LLM coding agents: look! a working compiler built in a few hours by an agent! this is amazing!

Anti-LLM coding agents: it's not a working compiler, though. And it doesn't matter how few hours it took, because it doesn't work. It's useless.

Pro: Sure, but we can get the agent to fix that.

Anti: Can you, though? We've seen that the more complex the code base, the worse the agents do. Fixing complex issues in a compiler seems like something the agents will struggle with. Also, if they could fix it, why haven't they?

Pro: Sure, maybe now, but the next generation will fix it.

Anti: Maybe. While the last few generations have been getting better and better, we're still not seeing them deal with this kind of complexity better.

Pro: Yeah, but look at it! This is amazing! A whole compiler in just a few hours! How many millions of hours were spent getting GCC to this state? It's not fair to compare them like this!

Anti: Anthropic said they made a working compiler that could compile the Linux kernel. GCC is what we normally compile the Linux kernel with. The comparison was invited. It turned out (for whatever reason) that CCC failed to compile the Linux kernel when GCC could. Once again, the hype of AI doesn't match the reality.

Pro: but it's only been a few years since we started using LLMs, and a year or so since agents. This is only the beginning!

Anti: this is all true, and yes, this is interesting. But there are so many other questions around this tech. Let's not rush into it and mess everything up.

View on HN

I'm reminded, once again, of the recent "vibe coded" OCaml fiasco[1].

The PR author had zero understanding why their entirely LLM-generated contribution was viewed so suspiciously.

The article validates a significant point: it is one thing to have passing tests and be able to produce output that resembles correctness - however it's something entirely different for that output to be good and maintainable.

[1] https://github.com/ocaml/ocaml/pull/14369

Damn... "AI has a very deep understanding of how this code works. Please challenge me on this." this person is something else. Just... wow.

This is the norm in my experience.

If you haven't come across a significant number of AI addicts as obnoxiously delusional as @Culonavirus describes, you must be getting close to retirement age.

People with any connection to new college graduates understand that this sort of idiotic LLM-backed arrogance is extremely common among low-to-mid-functioning twenty-somethings.

nice username

The Ai legal analysis seemed to be the nail in the coffin.

Adding Ai generated comments are IMHO some of the most rude uses of Ai.

Not sure what exactly you're referring to, but legal is a very interesting field to observe, right? I've been wondering about that since quite early in my LLM awareness:

A slightly sarcastic (or perhaps not so slightly..) mental model of legal conflict resolution is that much of it boils down to throwing lots of content at the opposing side, claiming that it shows that the represented side is right and creating a task for the opposite side to find a flaw in that material. I believe that this game of quantity fits through the whole range from "I'll have my lawyer repeat my argument in a letter featuring their letter head" all the way to paper-tsunamis like the Google-Oracle trial.

Now give both sides access to LLM... I wonder if the legal profession will eventually settle on some format of in-person offline resolution with strict limits to recess and/or limits to word count for both documents and notes, because otherwise conflicts fail to get settled in anyone's lifetime (or won by whoever does not run out of tokens first - come thinking of it, the technogarchs would love this, so I guess this is exactly what will happen barring a revolution)

Ah, sorry. I am not referring to using LLMs for legal work.

I am referring to the act of merely pasting the output of a model as a comment.

Have the decency to understand what the LLM is writing and write your own message.

That comment is wild

> Here's the AI-written copyright analysis...

I'm not going to spend more time reading than what you have spent writing!

What do you mean "not exactly sure what you are referring to"?

The guy just posted a huge ai slop pr, do you think that's the correct place for "very interesting field observations about legal"?

What else could it refer to than you can't back up copyright ownership questions with "ai said so"??

Some maintainers who drank the Kool-Aid, just use AI to answer to issues and review PRs.

Pretty soon we'll have AIs talking to each other.

I just read that whole thread and I think the author made the mistake of submitting a 13k loc PR, but other than that - while he gets downvoted to hell on every comment - he's actually acting professionally and politely.

I wouldn't call this a fiasco, it reads to me more that being able to create huge amounts of code - whether the end result works well or not - breaks the traditional model of open source. Small contributions can be verified and the merrit-vs-maintenance-effort can at least be assessed somewhat more realistically.

I have no bones in the "vibe coding sucks" vs "vibe coding rocks" discussion and I reading that thread as an outsider. I cannot help but find the PR author's attitude absolutely okay while the compiler folks are very defensive. I do agree with them that submitting a huge PR request without prior discussion cannot be the way forward. But that's almost orthogonal to the question of whether AI-generated code is or is not of value.

If I were the author, I would probably take my 13k loc proof-of-concept implementation and chop it down into bite-size steps that are easy to digest, and try to get them to get integrated into the compiler successively, with being totally upfront about what the final goal is. You'd need to be ready to accept criticism and requests for change, but it should not be too hard to have your AI of choice incorporate these into your code base.

I think the main mistake of the author was not to use vibe coding, it was to dream up his own personal ideal of a huge feature, and then go ahead and single-handedly implement the whole thing without involving anyone from the actual compiler project. You cannot blame the maintainers for not being crazy about accepting such a huge blob.

He is not polite, he is of the utmost rudeness. As a reply to being pointed to the fact that he copied so much code that the generated code included someone else's name in the License, his reply was https://github.com/ocaml/ocaml/pull/14369/changes/ce372a60bd...

I struggle to think how someone thinks this is polite. Is politeness to you just not using curse words?

Admittedly, his handling of this aspect was perhaps less than ideal, but I cannot see any impoliteness here whatsoever. As a matter of fact, I struggle to think how you could think otherwise.

But I am biased. After having lived a number of years in a country where I would say the average understanding of politeness is vastly different from where I've grown up, I've learned that there is just a difference of opinion of what is polite and what isn't. I have probably been affected by that too.

> but I cannot see any impoliteness here whatsoever.

Ah yes. "It's AI I don't care" and "AI has very deep reasoning about code, prove me wrong" are the height of politeness.

Well, I wouldn't necessarily call it "going out of your way to be accommodating", but impolite is just not the word I'd choose to characterize it. I can see why others might but it's just my personal feeling that I don't think that this is the correct adjective here.

That said, I don't feel like this topic is important enough to go on about it, I probably spend enough keystrokes on it already.

That's how politicians and passive-aggressive people hide their rudeness/impoliteness: under a veneer of polite-sounding phrases.

But I guess we could've used a few other synonyms: https://www.merriam-webster.com/thesaurus/impolite inconsiderate, thoughtless, impertinent (2nd meaning) :)

You sound like you'd characterize a thief as polite if he asked you please when taking your wallet.

Ah, I see what you mean - you're making a distinction between someone's speech and someone's acts. Fair enough. In that sense, you would argue that the action of dropping a 13k loc PR is impolite, and I can see that.

It's just that in my reading, I did not find his demeanor in the comment thread to be impolite. He was trying to sell his contribution and I think that whatever he wrote was using respectful language.

He responds to a thoughtful and detailed 600-word comment from a maintainer with a dismissive "Here's the AI-written copyright analysis..." + thousands of words of slop.

The effort asymmetry is what's rude. The maintainers take their project very seriously (as they should) and are generous enough with their time to invite contribution from outsiders. Showing up and dropping 13k lines of code, posting comments copy+pasted from a chat window, and insisting that your contribution is trustworthy not because you thought it through but because you fed it through a few LLMs shows that you don't respect the maintainers' time. In other words: you are being rude. They would have to put in more upfront effort to review your contribution than you put in to create it! Then they have to maintain it in perpetuity.

Dropping an unreviewable 13000 lines PR is disrespectful to the reviewers and their time.

Doing it without any prior discussion with the maintainers is disrespectful to the maintainers and the architecture work they put in.

Trying to "sell" your contribution is disrespectful and implies you know better than the maintainers.

Cockily saying "the AI knows better than you" is disrespectful.

Respectful and polite language does not prevent being disrespectful.

interpreting his words on a literal basis , the PR submitter isn't being directly impolite ...

if you will , place yourself in the shoes of the repository maintainer. a random person (with a personal agenda) has popped up trying to sell you a solution (that he doesn't understand) to a problem (that you don't see as problematic). after you spending literal hours patiently explaining why the proposition is not acceptable , this random person still continues attempting to sell his solution.

do you see any impoliteness in the reframed scenario ?

I think there's nothing wrong with trying to sell your solution, and I'm skeptical about the "literal hours" that you claim.

The way I interpret this thread is that the PR poster had a certain itch and came up with a vibe-coded solution that helped him. Now he's trying to make that available for others too. The maintainers don't want it because it's too large a PR to review properly and because they don't want to have to maintain it afterwards.

I can totally see both positions.

I was just referring to the fact that - in my opinion - unlike others here, his writing did not appear impolite to me. But you know, that's just me. I thought that he was trying to sell his code, and it's not unusual to get rejected at first, so I can't blame him for trying to defend his contribution. All I'm saying is that I thought he did so in a respectful manner, but of course you could argue that the whole endeavor was already an act of impoliteness, in a way?!

that is indeed what is being argued , is it possible to screw someone over politely ?

> his writing did not appear impolite to me

I learnt something from this thread.

That, respectfulness and politeness are more from intentions/actions than from speech alone. Politeness of language without any respect for the actual function of that speech is pointless. Indeed, that this what the LLMs are trained for. Form over function. And many humans get fooled by it and are also clueless like the person dropping the steaming turd of a PR.

simple: search that user. He's a grifter with many failed venues that recently started flooding big project with useless PRs

everybody should collectively tell him to fuck off

That may or may not be the case - I really was just going off this one thread, and how I personally read it. I completely appreciate that others read it differently.

"Why did you submit these files that are attributed to a completely unrelated person?"

"Beats me"

Do you consider this "professional and polite"? Raise your standards.

Minimally, I don't find this an unusual tone in the slightest for cs threads. But then again, I'm old.

I'm also quite surprised that apparently you cannot utter what is clearly just a personal opinion -- not a claim of objective truth -- without getting downvoted. But then again, the semantics of votes are not well-defined.

At the same time, I'm quite grateful for the constructive comments further down below under my original post.

however it's something entirely different for that output to be good and maintainable

People aren't prompting LLMs to write good, maintainable code though. They're assuming that because we've made a collective assumption that good, maintainable code is the goal then it must also be the goal of an LLM too. That isn't true. LLMs don't care about our goals. They are solving problems in a probabilistic way based on the content of their training data, context, and prompting. Presumably if you take all the code in the world and throw it in mixer what comes out is not our Platonic ideal of the best possible code, but actually something more like a Lovecraftian horror that happens to get the right output. This is quite positive because it shows that with better prompting+context+training we might actually be able to guide an LLM to know what good and bad looks like (based on the fact that we know). The future is looking great.

However, we also need to be aware that 'good, maintainable code' is often not what we think is the ideal output of a developer. In businesses everywhere the goal is 'whatever works right now, and to hell with maintainability'. When a business is 3 months from failing spending time to write good code that you can continue to work on in 10 years feels like wasted effort. So really, for most code that's written, it doesn't actually need to be good or maintainable. It just needs to work. And if you look at the code that a lot of businesses are running, it doesn't. LLMs are a step forward in just getting stuff to work in the first place.

If we can move to 'bug free' using AI, at the unit level, then AI is useful. Above individual units of code, like logic, architecture, security, etc things still have to come from the developer because AI can't have the context of a complete application yet. When that's ready then we can tackle 'tech debt free' because almost all tech debt lives at that higher level. I don't think we'll get there for a long time.

> People aren't prompting LLMs to write good, maintainable code though.

Then they're not using the tools correctly. LLMs are capable of producing good clean code, but they need to be carefully instructed as to how.

I recently used Gemini to build my first Android app, and I have zero experience with Kotlin or most of the libraries (but I have done many years of enterprise Java in my career). When I started I first had a long discussion with the AI about how we should set up dependency injection, Material3 UI components, model-view architecture, Firebase, logging, etc and made a big Markdown file with a detailed architecture description. Then I let the agent mode implement the plan over several steps and with a lot of tweaking along the way. I've been quite happy with the result, the app works like a charm and the code is neatly structured and easy to jump into whenever I need to make changes. Finishing a project like this in a couple of dozen hours (especially being a complete newbie to the stack) simply would not have been possible 2-3 years ago.

When I started I first had a long discussion with the AI... and made a big Markdown file with a detailed architecture description.

Yep, that's how you get better output from AI. A lot of devs haven't learned that yet. They still see it as 'better autocomplete'.

While this technique works for new projects, it takes no more than a couple of pivots for it to completely fail.

A good AI development framework needs to support a tail of deprecated choices in the codebase.

Skills are considerable better for this than design docs.

"It's just another Markdown file, bro".

LLMs do not learn. So every new session for them will be rebuilding the world from scratch. Bloated Markdown files quickly exhaust context windows, and agents routinely ignore large parts of them.

And then you unleash them on one code base that's more than a couple of days old, and they happily duplicate code, ignore existing code paths, ignore existing conventions etc.

That's why I'm very careful about how the context is constructed. I make sure all the relevant files are loaded with the prompt, including the project file so it can see the directory structure. Also keep a brief summary of the app functionality and architecture in the AGENTS.md file. For larger tasks, always request a plan and look through it before asking it to start writing code.

Yup, we've become reverse centaurs :) https://doctorow.medium.com/https-pluralistic-net-2025-09-11...

Not trying to be rude, but in a technology you're not familiar with you might not be able to know what good code is, and even less so if it's maintainable.

Finding and fixing that subtle, hard to reproduce bug that could kill your business after 3 years.

That's a fair point, my code is likely to have some warts that an experienced Android/Kotlin dev would wince at. All I know is that the app has a structure that makes an overall sense to me, with my 15+ years of experience as a professional developer and working with many large codebases.

The framing is key here. Is three years a long time? Both answers are right. Just getting a business off the ground is an achievement in the first place. Lasting three years? These days, I have clothes that don't even last that long. And then three years isn't very long at all. Bridges last decades. Countries are counted by centuries. Humanity is a millennia old. If AI can make me a company that's solvent for three years? Well, you decide.

I think we are going to have to find out what maintenance even looks like when LLMs are involved. "Maintainable" might no longer mean quite the same thing as it used to.

But it's not going to be as easy as "just regenerate everything". There are dependencies external to a particular codebase such as long lived data and external APIs.

I also suspect that the stability of the codebase will still matter, maybe even more so than before. But the way in which we define maintainability will certainly change.

> Then they're not using the tools correctly. LLMs are capable of producing good clean code, but they need to be carefully instructed as to how.

I'd argue that when the code is part of a press release or corporate blog post (is there even a difference?) by the company that the LLM in question comes from, e.g. Claude's C compiler, then one cannot reasonably assert they were "not using the tools correctly": even if there's some better way to use them, if even the LLM's own team don't know how to do that, the assumption should be that it is unreasonable to expect anyone else to how to do that either.

I find it interesting and useful to know that the boundary of the possible is a ~100kloc project, and that even then this scale of output comes with plenty of flaws.

Know what the AI can't do, rather than what it can. Even beyond LLMs, people don't generally (there's exceptions) get paid for manually performing tasks that have already been fully automated, people get paid for what automation can't do.

Moving target, of course. This time last year, my attempt to get an AI to write a compiler for a joke language didn't even result in the source code for the compiler itself compiling; now it not only compiles, it runs. But my new language is a joke language, no sane person would ever use it for a serious project.

That mirrors my experience so far. The AI is fantastic for prototyping, in languages/frameworks you might be totally unfamiliar with. You can make all sorts of cool little toy projects in a few hours, with just some minimal promoting

The danger is, it doesn't quite scale up. The more complex the project, the more likely the AI is to get confused and start writing spaghetti code. It may even work for a while, but eventually the spaghetti piles up to the point that not even more spaghetti will fix it

I'll get that's going to get better over the next few years, with better tooling and better ways to get the AI to figure out/remember relevant parts of the code base, but that's just my guess

>They are solving problems in a probabilistic way based on the content of their training data, context, and prompting.

>Presumably if you take all the code in the world and throw it in mixer what comes out is not our Platonic ideal of the best possible code, but actually something more like a Lovecraftian horror that happens to get the right output.

These statements are inaccurate since 2022 when LLMs started to have post training done.

>Here's my question: why did the files that you submitted name Mark Shinwell as the author?

>Beats me. AI decided to do so and I didn't question it.

Haha that's comedy gold, and honestly a good interview screening situation - you'd instantly pass on the candidate!

I once had a PR. I told the dev that "LLM is ok but you own the code"

He told me "I spent n days to architect the solution"

He shows me claude generated system design .. and then i say ok, I went to review the code. 1hr later i asked why did you repeat the code all over at the end. Dude replies "junk the entire PR it's AI generated"

Has anyone who's familiar with compiler source code tried to compare it to other compilers? Given that LLMs have been trained on data sets that include the source code for numerous C compilers, is this just (say) pcc extruded in Rust form?

I'm humbled by the maintainer's answer [0]. Must be great to work with people like him who have infinite patience and composure.

[0] https://github.com/ocaml/ocaml/pull/14369#issuecomment-35565...

gasche has been active on various forums over the years, and yes can confirm that he has infinite patience.

Yes, that comment by gasche is a very good general explanation for why vibe coded slop still doesn't cut it for contributing to any non-trivial FLOSS project. When you're building towards a large feature (DWARF support in this case) it's critical for contributions to be small and self-contained so that maintainers and reviewers don't get overwhelmed. As things stand, this means that human effort is an absolute requirement.

When contributions are small and tightly human-controlled it's also less likely that potential legal concerns will arise, since it means that any genuinely creative decisions about the code are a lot easier to trace.

(In this case, the AI seems to have ripped off a lot of the work from OxCaml with inconsistent attribution. OxCaml is actually license compatible (and friendly) with Ocaml but obviously any merge of that work should happen on its own terms, not as a side effect of ripoff slop code.)

> Must be great to work with people like him who have infinite patience and composure.

It is not just patience, he is ready to spent a shitload of time explaining basics to strangers. Such an answer would take, I believe would take a very least half an hour to compose, not counting the time you need to read all the relevant discussion to get the context. But yeah, it would be great to have more people like him around.

I get infuriated just from reading that, I wish I had as much patience as the maintainers on that project.

This to me sounds a lot like the SpaceX conversation:

- Ohh look it can [write small function / do a small rocket hop] but it can't [ write a compiler / get to orbit]!

- Ohh look it can [write a toy compiler / get to orbit] but it can't [compile linux / be reusable]

- Ohh look it can [compile linux / get reusable orbital rocket] but it can't [build a compiler that rivals GCC / turn the rockets around fast enough]

- <Denial despite the insane rate of progress>

There's no reason to keep building this compiler just to prove this point. But I bet it would catch up real fast to GCC with a fraction of the resources if it was guided by a few compiler engineers in the loop.

We're going to see a lot of disruption come from AI assisted development.

> the insane rate of progress

Yeah but the speed of progress can never catch the speed of a moving goalpost!

> Yeah but the speed of progress can never catch the speed of a moving goalpost!

How do you like those coast-to-coast self drives since the end of 2017?

What about the hype? If you claim your LLM generated compiler is functionally on par with GCC I’d expect it to match your claim.

I still won’t use it while it also matches all the non-functional requirements but you’re free to go and recompile all the software you use with it.

Training data only teaches it how to reach the goalpost, not how to overtake it.

Are we sure about that? I mean, we have seen that LLMs are able to generalize to some degree. So I don't see a reason why you couldn't put an agent in a loop with a profiler and have it try to optimize the code. Will it come up with entirely novel ideas? Unlikely. Could it potentially combine existing ideas in interesting, novel ways that would lead to CCC outperforming GCC? I think so. Will it get stuck along the way? Almost certainly.

The goalpost is not moving. The issue is that AI generates code that kinda looks ok but usually has deep issues, specially the more complex the code is. And that's not being really improved.

Would you want it to? The further the goal posts are the more progress we are making, and that's good, no? Trying to make it into a religious debate between believers and non-believers is silly. Neither side can predict the future, and, even if they could, winning the debate is not worth anything!

What is interesting is what can do with LLMs today and what we would like them to be able to do tomorrow so we can keep developing them into a good direction. Whether or not you (or I) believe it can do that thing tomorrow is thoroughly uninteresting.

You can be wrong on every step of your approximation and still be right in the aggregate. E.g. order of magnitude estimate, where every step is wrong but mistakes cancel out.

Human crews on Mars is just as far fetched as it ever was. Maybe even farther due to Starlink trying to achieve Kessler syndrome by 2050.

There are two questions which can be asked for both. The first one is "can these tech can achieve their goals?" which is what you seem debating. The other question is "is a successful outcome of these tech desirable at all?". One is making us pollute space faster than ever, as if we did not fuck the rest enough. They other will make a few very rich people even richer and probably everyone else poorer.

Interesting that people call this "progress" :)

> This to me sounds a lot like the SpaceX conversation

The problem is that it is absolutely indiscernible from the Theranos conversation as well…

If Anthropic stopped making lies about the current capability of their models (like “it compiles the Linux kernel” here, but it's far from the first time they do that), maybe neutral people would give them the benefit of the doubt.

For one grifter that happen to succeed at delivering his grandiose promises (Elon), how many grifters will fail?

All these people that built GCC and evolved the language did not have the end result in their training set. They invented it. They extrapolated from earlier experiences and knowledge, LLMs only ever accidentally stumble into "between unknown manifolds" when the temperature is high enough, they interpolate with noise (in so many senses). The people building GCC together did not only solve a to technical problem. They solved a social one, agreeing on what they wanted to build, for what and why. LLMs are merely copying these decisions.

That's true and I fully agree. I don't think LLMs' progress in writing a toy C compiler diminishes the achievements that the GCC project did.

But also we've just witnessed LLMs go from being a glorified line auto-complete tool to it writing a C compiler in ~3 years. And I think that's something. And noting how we keep moving the goal post.

GP: "it didn't write a C compiler, it copied other compilers. Writing one from scratch is a lot harder."

You: "but look! It wrote a C compiler!"

The pattern matching rote-student is acing the class. No surprises here. There is no need to understand the subject from first principles to ace tests. Majority of high-school and college kids know this.

> LLMs are merely copying these decisions.

This I strongly suspect is the crux of the boundaries of their current usefulness. Without accompanying legibility/visibility into the lineage of those decisions, LLM's will be unable to copy the reasoning behind the "why", missing out on a pile of context that I'm guessing is necessary (just like with people) to come up to speed on the decision flow going forward as the mathematical space for the gradient descent to traverse gets both bigger and more complex.

We're already seeing glimmers of this as the frontier labs are reporting that explaining the "why" behind prompts is getting better results in a non-trivial number of cases.

I wonder whether we're barely scratching the surface of just how powerful natural language is.

AI assist in software engineering is unambiguously demonstrated to some done degree at this point: the "no LLM output in my project" stance is cope.

But "reliable, durable, scalable outcomes in adversarial real-world scenarios" is not convincingly demonstrated in public, the asterisks are load bearing as GPT 5.2 Pro would say.

That game is still on, and AI assist beyond FIM is still premature for safety critical or generally outcome critical applications: i.e. you can do it if it doesn't have to work.

I've got a horse in this race which is formal methods as the methodology and AI assist as the thing that makes it economically viable. My stuff is north of demonstrated in the small and south of proven in the large, it's still a bet.

But I like the stock. The no free lunch thing here is that AI can turn specifications into code if the specification is already so precise that it is code.

The irreducible heavy lift is that someone has to prompt it, and if the input is vibes the output will be vibes. If the input is zero sorry rigor... you've just moved the cost around.

The modern software industry is an expensive exercise in "how do we capture all the value and redirect it from expert computer scientists to some arbitrary financier".

You can't. Not at less than the cost of the experts if the outcomes are non-negotiable.

What is FIM ?

All right, but perhaps they should also list the grand promises they made and failed to deliver on. They said they would have fully self-driving cars by 2016. They said they would land on Mars in 2018, yet almost a decade has passed since then. They said they would have Tesla's fully self-driving robo-taxis by 2020 and human-to-human telepathy via Neuralink brain implants by 2025–2027.

> - <Denial despite the insane rate of progress>

Sure, but not by what was actually promised. There may also be fundamental limitations to what the current architecture of LLMs can achieve. The vast majority of LLMs are still based on Transformers, which were introduced almost a decade ago. If you look at the history of AI, it wouldn't be the first time that a roadblock stalled progress for decades.

> But I bet it would catch up real fast to GCC with a fraction of the resources if it was guided by a few compiler engineers in the loop.

Okay, so at that point, we would have proved that AI can replicate an existing software project using hundreds of thousands of dollars of computing power and probably millions of dollars in human labour costs from highly skilled domain experts.

There's an argument to be made that replicating existing software is extremely useful.

Most of the time when you're writing a compiler for a new language, you'll be doing things that have been done before.

Because most of the concepts in your language are brought along from somewhere else.

That said: I'd always want a compiler and language designs to be well considered. Ideally, the authors have some proofs of soundness in their heads.

Perhaps LLM will make formal verification more feasible (from a cost perspective) and then our mind about what reliable software is might change.

In 1908 the Model T could do 45mph.

In 1935 the Auburn 851 S/C Speedster hit 100mph

In 1955 the Mercedes-Benz 300 SL Gullwing did 161mph

In 2025 the Yangwang U9 Xtreme hit 308mph

progress is a decaying exponential - Tsiolkovsky's tyranny

These specific points look like a line if you plot

And all these improvements past 1935 have been rendered irrelevant to the daily driver by safety regulations (I'll limit this claim to most of the continental US to avoid straying beyond my experience.)

The difference I see is that, after "get to orbit", the goalposts for SpaceX are things that have never been done before, whereas for LLMs the goalposts are all things that skilled humans have been able to do for decades.

Exactly. This flawed argument by which everything will be fixed by future models drives me crazy every time.

Just a couple more trillion and 6 more months!

That’s been the trend for a while. Can you make a prediction that says something concretely like “AI will not be able to do X by 2028” for a specific and well defined X?

Were any made about 2025?

In 2030, an AI model that I can run on my computer, without having to trust an evil megacorporation, will not be able to write a compiler for my markup language [0] based on a corpus of examples, without seeing the original implementation, using no more than 1.5× as much code as I did.

https://git.sr.ht/~xigoi/hilda

So far it has been accurate though. Models have gotten much better than even the most optimistic predictions.

No? The most optimistic predictions involved AGI around the corner, 6 months until no more developers for years now.

... Eh? A few years back, the usual suspects were predicting AGI by, usually, either 2026 or 2027. Think that's gonna happen?

(Such predictions have been quietly forgotten or revised forward, in general.)

No, I don't but it sounds very similar to the the naysayers that have silently moved the goalposts. That said, you're one of the few people in the wild that still claims LLMs are completely useless so I give you that.

You said:

> Models have gotten much better than even the most optimistic predictions.

We were promised Roko's Basilisk by now, damnit! Where's my magical robot god?!

But seriously, predictions a couple years back for 2026/27 (by quite big players, like Altman) were for AGI or as good as.

I do not, for the record, claim that they are totally useless. They are useful where correctness of results does not matter, for instance low-stakes natural language translation and spam generation. There's _some_ argument that they are somewhat useful in cases where their output can be reviewed by an expert (code generation etc), though honestly quantitive evidence there is mixed at best; for all the "10x developer" claims, there's not much in the way of what you'd call hard evidence.

> Pro: Sure, maybe now, but the next generation will fix it.

Do we need a c2 wiki page for "sufficiently smart LLM" like we do for https://wiki.c2.com/?SufficientlySmartCompiler ?

> This is still true - a compiler can never win this battle. All a human programmer has to do is take the output of the compiler and make a single optimisation, and he/she wins. This is the advantage that the human has - they can use any of a wide variety of tools at their disposal (including the compiler), whilst the compiler can only do what it was programmed. The best the compiler can hope for is a tie.

This is awkward

Pretty much. It's missing a tiny detail though. One side is demanding we keep giving hundreds of billions to them and at the same time promising the other side's unemployment.

> One side is demanding we keep giving hundreds of billions to them and at the same time promising the other side's unemployment.

That's a valid take. The problem is that there are, at this time, so many valid takes that it's hard to determine which are more valid/accurate than the other.

FWIW, I think this is more insightful than most of the takes I've seen, which basically amount to "side-1: we're moving to a higher level of abstraction" and "side-2: it's not higher abstraction, just less deterministic codegen".

I'm on the "higher level of abstraction" side, but that seems to be very much at odds with however Anthropic is defining it. Abstraction is supposed to give you better high-level clarity at the expense of low-level detail. These $20,000 burning, Gas Town-style orchestration matrices do anything but simplify high level concerns. In fact, they seem committed building extremely complex, low-level harnesses of testing and validation and looping cycles around agents upon agents to avoid actually trying to deal with whatever specific problem they are trying to solve.

How do you solve a problem you refuse to define explicitly? We end up with these Goodhart's Law solutions: they hit all of the required goals and declare victory, but completely fail in every reasonable metric that matters. Which I guess is an approach you make when you are selling agents by the token, but I don't see why anyone else is enamored with this approach.

You’re copping downvotes for this, but you’re not wrong.

“It will get better, and then we will use it to make many of you unemployed”

Colour-me-shocked that swathes of this industry might have an issue with that.

I don't feel that I see this anywhere but if so, I guess I'm in a third camp.

I am "pro" in the sense that I believe that LLM's are making traditional programming obsolete. In fact there isn't any doubt in my mind.

However, I am "anti" in the sense that I am not excited or happy about it at all! And I certainly don't encourage anyone to throw money at accelerating that process.

> I believe that LLM's are making traditional programming obsolete. In fact there isn't any doubt in my mind.

Is this what AI psychosis looks like? How can anyone that is a half decent programmer actually believe that English + non-deterministic code generator will replace "traditional" programming?

That's also my take, vibe coding as a non-deterministic 4GL. https://en.wikipedia.org/wiki/Fourth-generation_programming_...

4GLs are productive yes, but also limited, and still require someone to come up with specs that are both informed by (business) realities and engineering considerations.

But this is also an arena where bosses expect magic to happen when people are involved; just pronounce a new strategy, and your business magically transforms - without any of that pesky 'figuring out what to do' or 'aligning stakeholders' or 'wondering what drugs the c-suite is doing'. Let LLMs write the specs!

Of all takes, I find this most honest and believable. Not many would want a disruption of their stable life

And no-one ever stops and thinks about what it means to give up so much control.

Maybe one of those companies will come out on top. The others produce garbage in comparison. Capital loves a single throat to choke and doesn't gently pluralise. So of course you buy the best service. And it really can generate any code, get it working, bug free. People unlearn coding on this level. And some day, poof, Microsoft is coming around and having some tiny problem that it can generate a working Office clone. Or whatever, it's just an example.

This technology will never be used to set anyone free. Never.

The entity that owns the generator owns the effective means of production, even if everyone else can type prompts.

The same technology could, in a different political and economic universe, widen human autonomy. But that universe would need strong commons, enforced interoperability, and a cultural refusal to outsource understanding.

And why is this different from abstractions that came before? There are people out there understanding what compilers are doing. They understand the model from top to bottom. Tools like compilers extended human agency while preserving a path to mastery. AI code generation offers capability while dissolving the ladder behind you.

We are not merely abstracting labor. We are abstracting comprehension itself. And once comprehension becomes optional, it rapidly becomes rare. Once it becomes rare, it becomes political. And once it becomes political, it will not be distributed generously.

Nah bro it makes them productive. Get with the program. Amazing . Fantastic. Of course it resonates with idiots because they can't think beyond the vicinity of their own greed. We are doomed , noone gives two cents. Idiocracy is here and it's not Costco.

Sorry! Of course.

What an amazing tech. And look, the CEOs are promising us a good future! Maybe we can cool the datacenters with Brawndo. Let me ask chat if that is a good idea.

You could make same argument in "information superhighway" days, but it turned out to be the opposite: no company monopolised internet services, despite trying hard.

With so many companies in AI race it is already pretty competitive landscape and it doesnt seem likely to me that any of them can build deep enough moat to come ahead.

Internet services have been centralised into a few ISPs and a few websites everyone visits

a few? all sorts of websites and services are thriving on the Internet even after significant consolidation of attention social media caused. Not even close to a dystopian picture parent comment paints.

90% of eyeball views are using the 5 sites each filled with screenshots of the other 4

And not to mention that a C compiler is something we have literally 50 years worth of code for. I still seriously doubt the ability of LLMs to tackle truly new problems.

What do you classify as new? Every problem that we solve as developers is a very small deviation from already existing problems. Maybe that’s the point of llms?

How many developers do you think are solving truly novel problems? Most like me are CRUD bunnies.

And these developers do not write the majority of their codebase, they use tons of libraries and only write the glue code.

If your problem is a very small deviation from an existing problem, you should be able to take an existing open-source solution and make a very small modification to adapt it to your use case. No need for “vibe-coding” a lower-quality implementation from scratch.

Yeah, it kind of strikes me how a lot of the LLM use cases would actually be better served by existing techniques, like more/better libraries. And if that's not possible, it'd be way better to find the closest match, fork it, and make minimal modifications. At least then you have the benefit of an upstream.

But, sort of like cryptocurrency, the LLM people aren't so much trying to solve actual problems, but rather find an application of their existing technology. Sort of like the proverbial saying: when you're selling hammers, you want convince everyone that their problem as a nail.

As an Anti, my argument is "if AI will good in future, then come back in the future"

As a pro, my argument is "it's good enough now to make me incredibly productive, and it's only going to keep getting better because of advancements in compute".

I'd rather get really good at leveraging AI now than to bury my head in the sand hoping this will go away.

I happen to agree with the saying that AI isn't going to replace people, but people using AI will replace people who don't. So by the time you come back in the future, you might have been replaced already.

Why would anything you learn today be relevant tomorrow if AI keeps advancing? You would need less and less of all your tooling, markdown files and other rituals and just let the AI figure it out altogether.

So I can keep my job now so I can pay for compute in the future when I'm out of a job. The compute will be used to create my own business to make money.

Those are two different things though, and not everyone are stuck at a place enforcing token usage. And why would anyone pay you for something if all it takes is compute to make it? They would just make it themselves.

What makes you think you’ll be able to out-compete the purely-AI-led businesses with your business? What skills will give you an edge in the business that won’t also give you an edge in the job?

Maybe I can't. But that's also why I'm invested into AI companies right now.

Plan:

1. Keep my job for as long as I can by leveraging current AI tools to the best of my ability while my non-AI user colleagues lose earnings power or their job

2. Invest my money into AI companies and/or S&P500

3. If I'm truly rendered useless, live off of the investment

You got any better ideas? How would you do this?

I believe that I’ll keep enough of an edge in my job that I’ll continue to be employed. (At present I still have zero pressure to use AI, though I do use it.) It’s of course possible for that to turn out to be wrong, but in that case I also see no chance to start a business, and society will be in a lot of trouble.

  I believe that I’ll keep enough of an edge in my job that I’ll continue to be employed.

I don't believe I can. If I don't use AI tools at work, I'm for sure going to get fired and/or passed up for promotions.

> What makes you think you’ll be able to out-compete the purely-AI-led businesses with your business? What skills will give you an edge in the business that won’t also give you an edge in the job?

Or why do you think your small AI-driven business can survive against richer people who can pay for more compute and thus do better than you?

AI may just turn software into a pay to win game.

  Or why do you think your small AI-driven business can survive against richer people who can pay for more compute and thus do better than you?

I don't know. Maybe because of my creativity?

Anyways, I'm heavily invested in compute companies right now.

>> Or why do you think your small AI-driven business can survive against richer people who can pay for more compute and thus do better than you?

> I don't know. Maybe because of my creativity?

How would you keep that up? I think there's a false belief, especially common in business-inflected spaces (which includes the tech sector), that skills and abilities can be endlessly specialized (e.g. the MBA claim that they're experts at running businesses, any business). The more you outsource to AI the less creative you'll become, because you'll lose touch with the work.

You can only really be creative in spaces where you regularly get your hands dirty. Lose that, and I think your "creativity" will become the equivalent of the MBA offering the same cookie-cutter financial engineering ideas to every business (layoffs, buy back stock, FOMO the latest faddish ideas, etc).

> The compute will be used to create my own business to make money

tell me you've never seriously attempted starting a software business without telling me

It's like all these people for the last 2 decades "if only I knew how to code I'd make an app and be rich!" yeah sure you would

> I'd rather get really good at leveraging AI now than to bury my head in the sand hoping this will go away.

I don't think those are the only two options, though.

Further, "Getting really good at leveraging AI" is very different to "Getting really good at prompting LLMs".

One is a skill that might not even result in the AI providing any code. The other is a "skill" in much the same way as winning hotdog eating contests is a "skill".

In the latter, even the least-technical user can replace you once they get even halfway decent at min-maxing their agent's input (md files, although I expect we'll switch away from that soon enough to a cohesive and structured UI).

In the former, you had better find some really difficult problems that pay when you solve them.

Either way, I predict a lot of pain and anguish in the near future, for a lot of people. Especially those who expect that prompting skills are an actual "skill".

it sure is possible that One person using AI effectively may replace 10 people like me. it is just as likely that i may replace 10 people who only use AI.

I think you also forgot: Anti: But the whole thing can only have been generated because GCC and other compilers already exists (and depending on how strong the anti-feeling is: and has been stolen…)!

You didn't even mention that this vibe-coded toy compiler cost $20k in token spend. That's an insane amount of money for what this is.

It seems at least comparable to what you would have to pay a suitably competent developer to code up something similar.

> It seems at least comparable to what you would have to pay a suitably competent developer to code up something similar.

No. You could have someone of fiverr do it for $5. Download gcc, done.

If only the Claude team knew that, they could have saved a lot of tokens.

Two completely valid perspectives.

Unless you need a correctly compiled Linux kernel. In that case one gets exhausting real quick.

The perspective that says "a whole compiler in just a few hours" is making false claims. So not a valid perspective.

> this is all true, and yes, this is interesting. But there are so many other questions around this tech. Let's not rush into it and mess everything up.

That's a really nice fictitious conversation but in my experience "anti-ai" people would be prone to say "This is stupid LLM's will never be able to write complex code and attempting to do so is futile". If your mind is open to explore how LLM's will actually write complex software then by definition you are not "anti".

I don't think this is how pro and anti conversation goes.

I think the pro would tell you that if GCC developers could leverage Opus 4.6, they'd be more productive.

The anti would tell you that it doesn't help with productivity, it makes us less versed in the code base.

I think the CCC project was just a demonstration on what Opus can do now autonomously. 99.9% of software projects out there aren't building something as complex as a Linux compiler.

The "Anti" stance is only tenable now if you believe LLMs are going to hit a major roadblock in the next few months around which Big AI won't be able to navigate. Something akin to the various "ghosts in the machine" that started bedeviling EEs after 2000 when transistors got sufficiently small, including gate leakage and sub-threshold current, such that Dennard Scaling came to an abrupt end and clock speeds stalled.

I personally hope that that happens, but I doubt it will. Note also that processors still continued to improve even without Dennard Scaling due to denser, better optimized onboard caches, better branch prediction, and more parallelism (including at the instruction level), and the broader trend towards SoCs and away from PCB-based systems, among other things. So at least by analogy, it's not impossible that even with that conjectured roadblock, Big AI could still find room for improvement, just at a much slower rate.

But current LLMs are thoroughly compelling, and even just continued incremental improvements will prove massively disruptive to society.

> It's not fair to compare them like this!

As someone who leans pro in this debate, I don't think I would make that statement. I would say the results are exactly as we expect.

Also, a highly verifiable task like this is well suited to LLMs, and I expect within the next ~2 years AI tools will produce a better compiler than gcc.

The same two years as in "full self driving available in 2 years"?

Right.

These are different technologies with different rates of demonstrated growth. They have very little to do with each other.

Well let's check again in two years then.

Don't forget that gcc is in the training set.

That's what always puts me off: when AI replaces artists, SO and FOSS projects, it can only feed into itself and deteriorate..

it can feed into itself and improve. the idea that self-training necessarily causes deterioration is fanfic. remember that they spend massive amounts of compute on rl.

The AlphaZero approach shows otherwise, as long as there is an automated way to generate new test cases and evaluate the outcomes.

We can't do it for all domains, but I believe we can for efficient code.

today's models could be probably already good enough to compose tasks, and evaluate the results.

> I expect within the next ~2 years AI tools will produce a better compiler than gcc.

Building a "better compiler than gcc" is a matter of cutting-age scientific research, not of being able to write good code

Given that GCC is in the training data, it should not take much research to create an equally good compiler.

If reproducing data from the training set counts, then creating an equally good compiler is a matter of running `git clone` :D

But only if there is a competent compiler engineer running the AI, reviewing specs, and providing decent design goals.

Yes it will be far easier than if they did it without AI, but should we really call it “produced by AI” at that point?

Yes, we will certainly go that way, probably code already added to gcc has been developed through collaborative AI tools. Agree we don't call that "produced by AI".

I think compilers though are a rare case where large scale automated verification is possible. My guess is that starting from gcc, and all existing documentation on compilers, etc. and putting ridiculous amounts of compute into this problem will yield a compiler that significantly improves benchmarks.

> and I expect within the next ~2 years AI tools will produce a better compiler than gcc

and the "anti" crowd will point to some exotic architecture where it is worse

No, they will point out that the way to make GCC better is not really in the code itself. It's in scientific paper writing and new approaches. Implementation is really not the most work.

It seems that the cause of the difference in opinion is that the anti camp is looking at the current state while the pro camp looking at the slope and projecting it into the future.

> Pro-LLM coding agents: look! a working compiler built in a few hours by an agent! this is amazing!

> Anti-LLM coding agents: it's not a working compiler, though. And it doesn't matter how few hours it took, because it doesn't work. It's useless.

Also, from the Anti-LLM perspective: did the coding agent actually build a working compiler, or just plagiarize prior art? C compilers are certainly part of the LLM's training set.

That's relevant because the implication seems to be: "Look, the agent can successfully develop really advanced software!" when the reality may be that it can plagiarize existing advanced software, and will fall on its face if asked to do anything not already done before.

A lot of propaganda and hype follows the pattern of presenting things in a way to creating misleading implications in the mind of the listener that the facts don't actually support.

This is spot on, you can find traces of this conversation in the original thread posted on HN as well, where people are proclaiming "yeah it doesn't work, but still impressive!"

Reminds me so much of the people posting their problems about the tesla cybertruck and ending the post with "still love the truck though"

> Pro-LLM coding agents: look! a working compiler built in a few hours by an agent! this is amazing!

> Anti-LLM coding agents: it's not a working compiler, though. And it doesn't matter how few hours it took, because it doesn't work. It's useless.

Pro-LLM: Read the freaking article, it's not that long. The compiler made a mistake in an area where only two compilers exist that are up to the task: Linux Kernel.

Anti-LLM: isn’t all this intelligence supposed to give us something better than what we already have?

Me: Top 0.02%[1] human-level intelligence? Sure. But we aren't there yet.

[1] There are around 8k programming languages that are used (or were used) in practice (that is, they were deemed better than existing ones in some aspects) and there are around 50 million programmers. I use it to estimate how many people did something, which is objectively better than existing products.

Anthropic said they vibe-coded a C compiler that could compile the Linux kernel. That's what they said. No-one forced them to say that. They could have picked another code base.

It turns out that isn't true in all instances, as this article demonstrates. I'm not nearly expert enough to be able to decide if that error was simple, stupid, irrelevant, or whatever. I can make a call on whether it successfully compiled the Linux kernel: it did not.

I'm sorry for being excessively edgy, but "it's useless" is not a good summary for "linking errors after successfully compiling Linux kernel for x86_64."

> Because if it’s worth your time to lie, it’s worth my time to correct it.

https://www.astralcodexten.com/p/if-its-worth-your-time-to-l...

> Read the freaking article

The freaking article omits several issues in the "compiler". My bet is because they didn't actually challenged the output of the LLM, as it usually happens.

If you go to the repository, you'll find fun things, like the fact that it cannot compile a bunch of popular projects, and that it compiles others but the code doesn't pass the tests. It's a bit surprising, specially when they don't explain why those failures exist (are they missing support for some extensions? any feature they lack?)

It gets less surprising, though, when you start to see that the compiler doesn't actually do any type checking, for example. It allows dereferences to non-pointers. It allows calling functions with the wrong number of arguments.

There's also this fantastic part of the article where they explain that the LLM got the code to a point where any change or bug fix breaks a lot of the existing tests, and that further progress is not possible.

Then the fact that this article points out that the kernel doesn't actually link. How did they "boot it"? It might very well be possible that it crashed soon after boot and wasn't actually usable.

So, as usual, the problem here is that a lot of people look at LLM outputs and trust what they're saying they achieved.

The purpose of this project is not to create a state-of-the-art C compiler on par with projects that represent tens of thousands of developer-years. The goal is to assess the current capabilities of a largely autonomous software-building pipeline: it's not yet limitless, but better than it was. What a shocker.

I’ve had my share of build errors while compiling the Linux kernel for custom targets, so I wouldn’t be so sure that linker errors on x86_64 can’t be fixed with changes to the build script.

> The goal is to assess the current capabilities of a largely autonomous software-building pipeline: it's not yet limitless, but better than it was. What a shocker.

Of course, but we're trying to assess the capabilities by looking at the LLM output as if it were a program written by a person. If someone told me to check out their new C compiler that can build the kernel, I'd assume that other basic things, such as not compiling incorrect programs, are already pretty much covered. But with an LLM we can't assume that. We need to really check what's happening and not trust the agent's word for it.

And the reason why it's important it's because we really need to check whether it's actually "better than it was" or just "doing things incorrectly for longer". Let's say your goal was writing a gcc replacement. Does this autonomous pipeline get you closer? Or does it just get you farther away through the wrong path? Considering that it's full of bugs and incomplete implementations and cannot be changed without things breaking down, I'd say it seems to be the latter.

That's such a strawman conversation. Starting from:

> it's not a working compiler, though. And it doesn't matter how few hours it took, because it doesn't work. It's useless.

It works. It's not perfect, but anthropic claims to have successfully compiled and booted 3 different configurations with it. The blog post failed to reproduce one specific version on one specific architecture. I wish anthropic gave us more information about which kernel commits succeeded, but still. Compare this to years that it took for clang to compile the kernel, yet people were not calling that compiler useless.

If anyone thinks other compilers "just work", I invite them to start fixing packages that fail to build in nixos after every major compiler change, to get a dose of real world experience.

> Pro: but it's only been a few years since we started using LLMs, and a year or so since agents. This is only the beginning!

The billion dollar question is, can we get from 80% to 100%? Is this going to be a situation where that final gap is just insurmountable, or will the capabilities simply keep increasing?

I read a Youtube comment recently on pro AI video, it was

"The source code of gcc is available online"

You are missing the most important:

"Pro": give me tons of money to keep going this endeavour.

More seriously: if some LLM or other can _assist_ c++ to plain and simple C port...

This encompasses all the back-and-forth arguments I can think of. I would assume that proponents will eventually also mention AGI or ASI. :)

I think LLMs the technology is very cool and l’m frankly amazed at what it can do. What I’m ‘anti’ about is pushing the entire economy all in on LLM tech. The accelerationist take of ‘just keep going as fast as possible and it will work out, trust me bro’ is the most unhinged dangerous shit I’ve ever heard and unfortunately seems to be the default worldview of those in charge of the money. I’m not sure where all the AI tools will end up, but I am willing to bet big that the average person is not going to be better off 10 years from now. The direction the world is going scares the shit out of me and the usages of AI by bad actors is not helping assuage that fear.

Honestly? I think if we as a society could trust our leaders (government and industry) to not be total dirtbags the resistance to AI would be much lower.

Like imagine if the message was “hey, this will lead to unemployment, but we are going to make sure people can still feed their families during the transition, maybe look in to ways to support subsidies retraining programs for people whose jobs have been impacted .” Seems like a much more palatable narrative than, “fuck you pleb! go retrain as a plumber or die in a ditch. I’ll be on my private island counting the money I made from destroying your livelihood.”

This is a pattern I see a lot, in programming languages communities too, where it's a source a joy and dreams first and facts later.

Maybe Anthropic can sponsor a research team to polish this using just an agent. A lot of things can be learned from that exercise.

We could be colonizing Mars with Claude Code and there will always be some skeptic somewhere.

Two thoughts here:

First, remember when we had LLMs run optimisation passes last year? Alphaevolve doing square packing, and optimising ML kernels? The "anti" crowd was like "well, of course it can automatically optimise some code, that's easy". And things like "wake me up when it does hard tasks". Now, suddenly when they do hard tasks, we're back at "haha, but it's unoptimised and slow, laaame".

Second, if you could take 100 juniors, 100 mid level devs and 100 senior devs, lock them in a room for 2 weeks, how many working solutions that could boot up linux in 2 different arches, and almost boot in the third arch would you get? And could you have the same devs now do it in zig?

The thing that keeps coming up is that the "anti" crowd is fighting their own deamons, and have kinda lost the plot along the way. Every "debate" is about promisses, CEOs, billions, and so on. Meanwhile, at every step of the way these things become better and better. And incredibly useful in the right hands. I find it's best to just ignore the identity folks, and keep on being amazed at the progress. The haters will just find the next goalpost and the next fight with invisible entities. To paraphrase - those who can, do, those who can't, find things to nitpick.

First off Alpha Evolve isn't an LLM. No more than a human is a kidney.

Second depends. If you told them to pretrain for writing C compiler however long it takes, I could see a smaller team doing it in a week or two. Keep in mind LLMs pretrain on all OSS including GCC.

> Meanwhile, at every step of the way these things become better and better.

Will they? Or do they just ingest more data and compute?[1] Again, time will tell. But to me this seems more like speed-running into an Idiocracy scenario than a revolution.[2]

I think this will turn out another driverless car situation where last 1% needs 99% of the time. And while it might happen eventually it's going to take extremely long time.

[1] Because we don't have much more computing jumps left, nor will future data be as clean as now.

[2] Why idiocracy?

Because they are polluting their own corpus of data. And by replacing thinking about computers, there will be no one to really stop them.

We'll equalize the human and computer knowledge by making humans less knowledgeable rather than more.

So you end up in an Idiocracy-like scenario where a doctor can't diagnose you, nor can the machine because it was dumbed down by each successive generation, until it resembles a child's toy.

> First off Alpha Evolve isn't an LLM.

It's a system based on LLMs.

> AlphaEvolve, an evolutionary coding agent powered by large language models for general-purpose algorithm discovery and optimization. AlphaEvolve pairs the creative problem-solving capabilities of our Gemini models with automated evaluators that verify answers, and uses an evolutionary framework to improve upon the most promising ideas.

> AlphaEvolve leverages an ensemble of state-of-the-art large language models: our fastest and most efficient model, Gemini Flash, maximizes the breadth of ideas explored, while our most powerful model, Gemini Pro, provides critical depth with insightful suggestions. Together, these models propose computer programs that implement algorithmic solutions as code.

It’s more like a concept car vs a production line model. The capabilities it has were fine tuned for a specific scenario and are not yet available to the general public.

> It's a system based on LLMs.

What you said is:

    > First, remember when we had LLMs run optimisation passes last year? Alphaevolve doing square packing

If I start a sentence:

    First, remember the fish intelligence competition last year? Rossie jumped through a hula hoop.

I, and other readers (probably), would think Rossie is a fish. Not a dog. Even if you can technically group dogs as a sort of fish descendant.

I have no idea what you're arguing. Alphaevolve is similar to claude code. They are using LLMs in a harness. No idea what you mean with fish, kidneys and so on. Can you please stick to the technical stuff? Otherwise it's just noise.

I'm arguing your writing is unclear and confusing. You can't continue a sentence and pretend the new sentence isn't related to the previous one.

Alpha Evolve is made from LLMs, but it's not the only part. If anything, it needs a genetic algo component. LLMs generally don't evolve.

Also, why are you focusing on AlphaEvolve? I made two other points you haven't addressed.

You have no idea what alphaevolve is, yet you try to correct me. This isn't productive, I'm out.

First off, let's say I'm wrong about Alpha Evolve. Fine, I made two more points; address them as well; that's just normal manners in a conversation.

Second, I question your idea of what Alpha Evolve is. You seem to think it's an LLM or LLM-adjacent when it's more like an evolutionary algo picking a better seed among the LLMs. That's not an LLM, if anything, it has some ability to correct itself.

You're heavily implying that because it can do this task, it can do any task at this difficulty or lower. Wrong. This thing isn't a human at the level of writing a compiler, and shouldn't be compared to one

Codex frustratingly failed at refactoring my tests for me the other day, despite me trying many, many prompts of increasing specificity. A task a junior could've done

Am I saying "haha it couldn't do a junior level task so therefor anything harder is out of reach?" No, of course not. Again, it's not a human. The comparison is irrelevant

Calculators are superhuman at arithmetic. Not much else, though. I predict this will be superhuman at some tasks (already is) and we'll be better at others

Adopt this half baked, half broken, insanely expensive, planet destroying, IP infringing tech, you have no choice.

Burn everything, because if you don’t, you will get left behind and, maybe, just maybe, in 2 years when it’s good enough, maybe… after hoovering up all the money, IP and domain expertise for free, and you’ve burnt all your money & sanity prompting and cajoling it to a semi working solution for a problem you didn’t really have in the first place, it will dump you at the back of the unemployment line. All hail the AI! Crazy times.

In the meantime please enjoy targeted scams, ever increasing energy prices, AI content farms, hardware shortages, and endless, endless slop.

When humans architect anything - ideas, buildings, software or ice cream sundaes, we make so many little decisions that affect the overall outcome, we don’t even know or think about it! Too many sprinkles and sauce and it will be too sweet and hard to eat. We make those decisions based on both experience and imagination. Watch a small child making one to see the perfect human intersection of these two things at play. The LLM totally lacks the imagination part, except in the worst possible ways. It’s experience includes all sorts of random internet garbage that can sound highly convincing even to domain experts. Now it’s training set is being further expanded with endless mountains of more highly impressive sounding garbage.

It was obvious to me with the first image gen models how incredibly impressive it was to see an image gradually forming from the computer based on nothing but my brief text input but also how painfully limited the technology would always be. After days and days of early obsessive image generation, I was no better as an artist than when I began! Everything also kind of looked the same as well?

As incredible as it was, it was nothing more than a massively complicated, highly advanced parlour trick. A futuristic, highly powerful pattern generator. Nothing has changed my mind at all. All that’s happened is we’ve seen the worst tricksters, shysters and con artists jump on a very dangerous bandwagon to hell and try and whip us less compliant souls onboard.

Lots of things follow patterns, the joy in life, for me, is discovering the patterns, exploring them and developing new unique and interesting patterns.

I’ve yet to encounter a bandwagon worth joining anyway, maybe this will be the one that leaves me behind and i’ll be forced to retire on cartoon gorilla NFTs and tulip farming?

> The thing that keeps coming up is that the "anti" crowd is fighting their own deamons, and have kinda lost the plot along the way

perfect example

What does this imagined conversation have to do with the linked article? The “pro” and “anti” character both sound like the kind of insufferable idiots I’d expect to encounter on social media, the OP is a very nice blog post about performance testing and finding out what compilers do, doesn’t attempt any unwarranted speculation about what agents “struggle with” or will do “next generation”, how is it an example of that sort of shitposting?

I'm firmly in the anti/unimpressed camp so far - but of course open to see where it goes.

I mean this compiler is the equivalent of handing someone a calculator when it was first invented and seeing that it took 2 hours to multiply two numbers together, I would go "cool that you have a machine that can do math, but I can multiply faster by hand, so it's a useless device to me".

I mean - who would honestly expect an LLM to be able to compete with a compiler with 40 years of development behind it? Even more if you count the collective man years expended in that time. The Claude agents took two weeks to produce a substandard compiler, under the fairly tight direction of a human who understood the problem space.

At the same time - you could direct Claude to review the register spilling code and the linker code of both LLVM/gcc for potential improvements to CCC and you will see improvements. You can ask it not to copy GPL code verbatim but to paraphrase and tell it it can rip code from LLVM as long as the licenses are preserved. It will do it.

You might only see marginal improvements without spending another $100K on API calls. This is about one of the hardest projects you could ask it to bite off and chew on. And would you trust the compiler output yet over GCC or LLVM?

Of course not.

But I wager, that if you _started_ with the LLVM/gcc codebases and asked it to look for improvements - it might be surprising to see what it finds.

Both sides have good arguments. But this could be a totally different ball game in 2, 5 and 10 years. I do feel like those who are most terrified by it are those whose identity is very much tied to being a programmer, and seeing the potential for their role to be replaced and I can understand that.

Me personally - I'm relieved I finally have someone else to blame and shout at rather than myself for the bugs in the software I produce. I'm relieved that I can focus now on the more creative direction and design of my personal projects (and even some work projects on the non-critical paths) and not get bogged down in my own perfectionism with respect to every little component until reaching exhaustion and giving up.

And I'm fascinated by the creativity of some of the projects I see that are taking the same mindset and approach.

I was depressed by it at first. But as I've experimented more and more, I've come to enjoy seeing things that I couldn't ever have achieved even with 100 man years of my own come to fruition.

Are you trying to demonstrate a textbook example of straw man argument?

Um actually, it's called a Steel Man argument.

I learned about it from HackerNews and ChatGPT.

In my experience, it is often the other way around. Enthusiasts are tasked with trying to open minds that seem very closed on the subject. Most serious users of these tools recognize the shortcomings and also can make well-educated guesses on the short term future. It's the anti crowd who get hellbent on this ridiculously unfounded "robots are just parrots and can't ever replace real programmers" shtick.

Maybe if AI evangelists would stop lying about what AI can do then people would hate it less.

But lying and hype is baked into the DNA of AI booster culture. At this point it can be safely assumed anything short of right-here-right-now proof is pure unfettered horseshit when coming from anyone and everyone promoting the value of AI.

Your comment is a perfect example of the biases I'm talking about. "AI evangelists" are not a singular group of people.

You're right! Sometimes even the right-here-right-now claims of AI capabilities are horseshit too with people in actuality remotely controlling the product.

It's not common for present-capabilities to be lied about too. But it does happen!

And the smallest presence are the users who don't work in the AI industry but rave about AI. I know of...two....people who fit that bill. A lead developer at a cybersecurity firm and someone who works heavily in statistics and data analytics. Both of which are very senior people in their fields who can articulate exactly what they're looking for without much left to interpretation.

Now you're just presenting straw man arguments and continuing to conflate separate issues.

No no - I am agreeing with you that AI evangelists are not a singular group of people! Im fact I agreed so much I even gave a couple examples of how they're not a monolithic group!

Reply on news.ycombinator.com