Hacker News Reader

Comment by kevindamm | Hacker News Reader

Salient point:

> Would I have been able to do it without ChatGPT? Certainly yes, but the most interesting thing is not the fact that it would have taken me longer: the truth is that I wouldn't even have tried, because it wouldn't have been worth it.

This is the true enabling power of LLMs for code assistance -- reducing the activation energy of new tasks enough that they are tackled (and finished) when they otherwise would have been left on the pile of future projects indefinitely.

I think the internet and the open source movement had a similar effect, in that if you did not attempt a project that you had some small interest in, it would only be a matter of time before someone else did enough of a similar problem for you to reuse or repurpose their work, and this led to an explosion of (often useful, or at least usable) applications and libraries.

I agree with the author that LLMs are not by themselves very capable but provide a force multiplier for those with the basic skills and motivation.

View on HN

I find that even beyond "activation energy", a lot of my exploration with ChatGPT is around things I don't necessarily initially even intend to take forward, but is just curious about, and then realise I can do with much less effort than I expected.

You can often get much of the same effect by bouncing ideas of someone, who doesn't necessarily need to know the problem space well enough to solve things but just well enough to give meaningful input. But people with the right skills aren't available at the click of a button 24/7.

I feel very left out of all this LLM hype. It's helped me with a couple of things, but usually by the time I'm at a point where I don't know what I'm doing, the model doesn't know any better than I do. Otherwise, I have a hard time formulating prompts faster than I can just write the damn code myself.

Am I just bad at using these tools?

No, you're likely just a better programmer than those relying on these tools.

That could be the case and likely is in areas where they are strongest, just like the articles example of how its not as useful for systems programming because he is an expert.

If you ask it about things you don't know it was likely trained on high quality data for and get bad answers, you likely need to improve your writing/prompting.

Except it's most dangerous when used in areas that you're weakest because it will confidently spit out subtly wrong answers to everything. It is not a fact engine.

That only matters if you use it for things where failure actually causes damage.

Its useful for writing generic code/template/boilerplate, then customizing it by inserting your own code. For something you already know better, there isn't a magic prompt to express it, since the code is not generic enough for LLM to understand as a prompt.

Its best usecase is when you're not a domain expert, need quickly to run some unknown API/library inside your program inserting code like "write a function for loading X with Y in language Z" when you barely have an idea what is X,Y,Z. Its possible in theory to break-down everything to "write me a function for N" but the quality of such functions is not worth the prompting in most situations and you better ask it to explain how to write a function X,Y,Z step-by-step.

This is exactly where I get the most value. For example, I know write a bunch of custom chrome plugins. I'm not much of javascript guy, but I can get by and validate the code. Usually what I want to do is simple, but requires making an api call and basic parsing. All stuff I could probably figure out myself in an hour or two. But instead I can get an initial version done in 2 minutes and spend 5-10 debugging. I probably wouldn't even try otherwise.

You can use LLMs as documentation lookups for widely used libraries, eg: the Python stdlib. Just place a one line comment of what you want the AI to do and let it autocomplete the next line. It’s much better than previous documentation tools because it will interpolate your variables and match your function’s return type.

As the article says, it helps to develop an intuition for what the models are good or bad at answering. I can often copy-paste some logs, tracebacks, and images of the issue and demand a solution without a long manual prompt - but it takes some time to learn when it will likely work and when it's doomed to fail.

This is likely the biggest disconnect between people that enjoy using them and those that don’t. Recognizing when GPT-4’s about to output nonsense and stopping it in the first few sentences before it wastes your time is a skill that won’t develop until you stop using them as if they’re intended to be infallible.

At least for now, you have to treat them like cheap metal detectors and not heat-seeking missiles.

I've developed a workflow that's working pretty well for me. I treat the LLM as a junior developer that I'm pair programming with and mentoring. I explain to it what I plan to work on, run ideas by it, show it code snippets I'm working on and ask it to explain what I'm doing, and whether it sees any bugs, flaws, or limitations. When I ask it to generate code, I read carefully and try to correct its mistakes. Sometimes it has good advice and helps me figure out something that's better than what I would have done on my own. What I end up with is like a living lab notebook that documents the thought processes I go through as I develop something. Like you, for individual tasks, a lot of times I could do it faster if I just wrote the damn code myself, and sometimes I fall back to that. In the longer term I feel like this pair programming approach gives me a higher average velocity. Like others are sharing, it also lowers the activation energy needed for me to get started on something, and has generally been a pretty fun way to work.

Here's what I find extremely useful:

1 - very hit or miss -- I need to fidget with the aws api in some way. I use this roughly every other month, and never remember anything about it between sessions. ChatGPT is very confused by the multiple versions of the APIs that exist, but you can normally talk it into giving you a basic working example that is then much easier to modify into exactly what I want than starting from scratch. Because of the multiple versions of the aws api, it is extremely prone to hallucinating endpoints. But if you persist, it will eventually get it right enough.

2 - I have a ton of bash automations to do various things. just like aws, I touch these infrequently enough that I can never remember the syntax. chatgpt is amazing and replaces piles of time googling and swearing.

3 - snippets of utility python to do various tasks. I could write these, but chatgpt just speeds this up.

4 - working first draft examples of various js libs, rails gems, etc.

What I've found has extremely poor coverage in chatgpt is stuff where there are basically no stackoverflow articles explaining it / github code using it. You're likely to be disappointed by the chatgpt results.

I'd reframe that slightly: it's not that you are bad at using these tools, it's that these tools are deceptively difficult to use effectively and you haven't yet achieved the level of mastery required to get great results out of them.

The only way to get there is to spend a ton of time playing with them, trying out new things and building an intuition for what they can do and how best to prompt them.

Here's my most recent example of how I use them for code: https://til.simonwillison.net/github-actions/daily-planner - specifically this transcript: https://gist.github.com/simonw/d189b737911317c2b9f970342e9fa...

Yeah, I’m not sure how often these tools will really help me with the things that end up destroying my time when programming, which are stuff like:

1) Shit’s broken. Officially supported thing kinda isn’t and should be regarded as alpha-quality, bugs in libraries, server responses not conforming to spec and I can’t change it, major programming language tooling and/or whatever CI we’re using is simply bad. About the only thing here I can think of that it might help with is generating tooling config files for the bog standard simplest use case, which can sometimes be weirdly hard to track down.

2) Our codebase is bad and trying to do things the “right” way will actually break it.

One thing you might find useful is using it to write unit tests for legacy code, that more easily allow you to refactor the crappy codebase.

I give you an example. I took advantage of some free time in these days to finally implement some small services on my home server. ChatGPT (3.5 in my case) has read the documentation of every language, framework, API out there. I asked it to start with Python3 http.server (because I know it's already on my little server) and write some code that would respond to a couple of HTTP calls and do this and that. It created an example that customized the do_GET and do_POST methods of http.server, which I didn't even know exist (the methods.) It did do well also when I asked it to write some simple web form. It did not so well when things got more complicated but at that point I already knew how to proceed. I finished everything in three hours.

What did it save me?

First of all the time to discover the do_GET and do_POST methods. I know that I should have read the docs but it's like asking a colleague "how do I do that in Python" and getting the correct answer. It happens all the time, sometimes it's me to ask, sometimes it's me to answer.

Second, the time to write the first working code. It was by no means complete but it worked and it was good enough to be the first prototype. It's easier to build on that code.

What it didn't save me? All the years spent to recognize what the code written by ChatGPT did and to learn how to go on from there. Without those years on my own I would have been lost anyway and maybe I wouldn't been able to ask it the right questions to get the code.

I've been learning boring old SQL over the last few months, and I've found the AIs quite helpful at pointing out some things that are perhaps too obvious for the tutorials to call out.

I don't mind taking suggestions about code from an AI because I can immediately verify the AI's suggestion by running the code, make small edits, and testing it.

But this is my pet peeve when people claim this; the only reason is because the AI code is small and constrained in scope. Otherwise the very claim that humans can easily verify AI code quickly would, like, violate Rice's Theorem.

That's an underutilization of the complexity theory. Since not all problems are formulated as being Turing-complete, there are better theorems to apply than Rice's Theorem, such as:

* IP=PSPACE (you can verify correctness of any PSPACE computation in polynomial time)

* NIP=NEXPTIME (you can verify correctness of any NEXPTIME computation with two non-cooperative provers)

* NP=PCP(1,log(n)) (you can verify correctness of any NP statement with O(log(n)) bits of randomness by sampling just O(1) bits from a proof)

What these means is that a human is indeed able to verify correctness of the output of a machine with stronger computational abilities than the human itself.

Regarding your last point about what it didn't save you, it reminded me of this blog post: https://overbring.com/articles/2023-06-23-on-using-llm-to-ge...

I had good results by writing my requirements like they were very, high-level code. I told it specifically what to do. Like formal specifications but with no math or logic. I usually defined the classes or data structures, too. I’d also tell it what libraries to use after getting their names from a previous, exploratory question.

From there, I’d ask it to do one modification at a time to the code. I’d be very precise. I’d give it only my definitions and just the function I wanted it to modify. It would screw things up whereby I’d tell it that. It would fix its errors, break working code with hallucinations, and so on. You need to be able to spot these problems to know when to stop asking it about a given function.

I was able to use ChatGPT 3.5 for most development. GPT 4 was better for work needed high creativity or lower hallucinations. I wrote whole programs with it that were immensely useful, including a HN proxy for mobile. Eventually, ChatGPT got really dumb while outputting less and less code. It even told me to hire someone several times (?!). That GPT-3-Davinci helped a lot suggests it’s their fine-tuning and system prompt causing problems (eg for safety).

The original methods I suggested should work, though. You want to use a huge, code-optimized model for creativity or hard stuff, though. Those for iteration, review, etc can be cheaper.

I felt the same every time I tried to get some help in a subject matter where my knowledge was quite advanced and/or when the subject matter was obscure/niche.

Whenever I tried it on something more common and/on in some stuff I had absolutely zero familiarity it did help me bootstrap quicker than reading some documentation would have

That tells a lot about how hard it is to write/find documentation that is tailored exactly to you and your needs

However could it be that the 'entertainment effect' of using a new (and trendy) technology like LLMs provides the activation energy for otherwise mundane tasks?

This is true. I write way more documentation now since llm does all the formatting, structure , diagrams ect. I just guide it at a high level.

Do you use a specialized LLM for diagrams?

I just ask chatgpt to generate text diagrams that i can embed in my markdown.

I'm not OP, but I just ask GPT to turn code or process or whatever else into a mermaid diagram. Most of the time I don't even need to few-shot prompt it with examples. Then you dump the resulting text into something like https://mermaid.live/ and voilà.

No. I've completed projects that have been on the back burner for years in hours. They weren't on the back burner for lack of interest but mainly for lack of expertise in a specific stupid area.

It's not an exaggeration to say that I now do two weeks of programming a night. Of course a lot of times the result gets thrown away because the fundamental idea was flawed in a non-obvious way. But learning that is also worth while.

It's revolutionized our in house tooling at work.

No longer do I need to give PR feedback more than a couple times, because we can just ask chatgpt to come up with a lint rule that detects and sometimes auto-fixes the issue. I use it to write or change Jenkins jobs, scaffold out tests, diagram ideas from a monologue brain dump, write alerting and monitoring code, write and clean up documentation.

Most recently I wanted to get some "end of year" stats for the teams, normally it would never have happened because I don't have half a day to dedicate to relearning the git commands, and how to count the lines of code and attribute changes to teams and script the whole process to work across 20 repos.

20 minutes later with chatgpt I had results I could share within the company.

It's just allowed me to skip almost all of the boring and time consuming parts of handling small things like that, and instead turns me into a code reviewer who makes a few changes to make it good enough then pushes it out

Wait what?

ChatGPT does diagrams for you? Writes documentation?

Absolutely!

I found a plugin a while back called "AI Diagrams" that generates whimsical.com diagrams for me. Combined with the "speech to text" systems in chatgpt means I can just start babbling about some topic and let it write it all down, collect it into documentation, and even spit out a few diagrams from it.

I generally have to spend like 10 minutes cleaning them up and rearranging them to look a bit more sane, but it's been a godsend!

Similarly I sometimes paste a bunch of code in and tell it to write some starter docs for this code, then I can go from there and clean it up manually, or just tell it what changes need to be made. (technically I tend to use editor plugins these days not copy+paste, but the idea is the same)

Other times I'll paste in docs and have it reformat them into something better. Like I recently took our ~3 year old README in a monorepo that goes over all the build and lint commands and had it rearrange everything into sets of markdown tables which displayed the data in a much easier to understand format.

Does your company have any considerations for feeding chatGPT source code? Would it not be safer to use a local LLM?

Not any more than feeding source code to Github. (I personally feel "source code" is very rarely the "secret sauce" of a company anyway). But where I work we not only have the blessing of the company, we are encouraged to use it because they've clearly seen the benefits it brings.

A local LLM would be preferrable all things equal, but in my experience for this kind of stuff, GPT-4 is just so much better than anything else available, let alone any local LLMs.

It's safe if you use the OpenAI API, or you have an enterprise chatgpt account - they have the same privacy guarantees as other cloud providers there.

Same here - I feel as though it's turned me into a super programmer. One of my favorite uses is converting a C# model with a bunch of properties into a SQL table along with their corresponding stored procedures. I used to have boilerplate code and would have to copy/paste every property, along with their SQL datatypes. One model might take me 10 to 20 minutes to get translated to a table, and the stored procedures would take me another 20 minutes. Now it's all done in 5 minutes tops, and I'm not having to nitpick datatype issues I may have screwed up in the manual process.

In my experience, it genuinely lowers the activation (and total) energy for certain tasks, since LLMs are great at writing repetitive code that would otherwise be tedious to write by hand. For instance, writing a bunch of similar test cases.

I had a project recently: building an advanced Java class file analyzer. I knew a lot about ow2 asm libraries, but it saved me a lot of digging time remembering exact descriptor formats. Also it helped me understand why other static analysis libraries weren't good enough for me for stateful reasons.

For me, ChatGPT is doing two things: 1) saving trivial StackOverflow and library code walking to answer specific question, and 2) helping the initial project research stage to grasp feasibility of approaches I may take before starting.

to add to that I've heard a lot of people who have things like ADHD saying LLM's are life changing more than say neurotypical people. For those of us with bad ADHD doing simple things are the hardest, just taking out the trash or opening the mail is nearly impossible, your internal dialog is screaming at you for hours to just do the thing, but your body won't listen. They call it executive dysfunction, but it's the bane of my life

LLM's helping to just start the thing is actually a huge deal.

Also, just throwing a bunch of disorganised thoughts into it, and letting it organise everything.

Agreed, I've now got a sizable project going that I would probably procrastinate on attempting for years without GPT 4 laying the initial groundwork, along with informing me of a few libraries I had never heard of that reduced wheel reinventing quite a bit.

First automation acts as a powerful lever and enabler, then it replaces you.

In 5 years time you may well be more productive than ever. In 15 years I doubt there'll be many programming jobs in the form they are recognisable today.

Historically, automation has always made society richer and better off as a result.

There are two guys outside of my window at this very moment getting rid of a huge pile of dirt. One is in an excavator, the other in a truck. There’s a bunch of piles that they’ve taken care of today. Two centuries ago this work would’ve taken a dozen people, a few animals of burden, and a lot more time.

Where are the other ten hypothetical people? I don’t know, but chances are they’ve been absorbed by the rest of the economy doing something else worthwhile that they are getting paid for.

Those ten hypothetical people would likely have actually been zero because the task wouldn't have been worth hiring ten people.

Important, and often ignored! Technological improvements change the cost structure of activities. Consider texting. We send billions of texts every day. This does not replace billions of couriers. Rather, more people work to maintain our phone supply and telecom than we ever had running around with letters. It's not a promise but it is a pattern.

also, two centuries ago, we didn't have trucks and the concomitant infrastructure, jobs, wealth, etc. that machines brought along.

> Where are the other ten hypothetical people?

Zoned out somewhere in the backstreets of SF

Or dead because Trump cut off their welfare.

This comment and the grandparent can both be right. Society gets richer because automation replaces jobs, leaving us more time to do other jobs.

I agree, on a societal level it's a great benefit.

On an individual level, however, I'd suggest keeping an eye out for opportunities to retrain.

As an analogy, I'd rather be like the coal miners in the 80s who could read the writing on the wall and quietly retrained into something else rather than those who spent their better years striking over cuts to little avail.

It's a very daunting prospect seeing a path to unemployability, though.

Depending how quickly the change happens, it could be a gentle transition, or it could upset a lot of people.

Yeah, but what do you retrain to? I can't think of any industry that isn't being threatened with massive automation.

Well, the AI job market is pretty hot, so that's an option. And I expect as things mature it'll only create even more opportunity. Projects that nobody previously would have considered, because they'd have taken too long, required too much training for too many people? Now they can happen! And for each of those things, jobs are created, not taken away.

Imagine yourself as CEO. What do you think is your most likely train of thought? A/ "I can fully replace my labor force with bots" or B/ "My employees now have superpowers to do things we couldn't even conceive of two years ago". While there are certainly some scenarios where the first choice is appropriate, the latter sounds far far more likely in most scenarios to me. Why would you contract when there's suddenly so much opportunity to expand?

What AI jobs?

There are two problems with this argument. The first, and easier to accept one is that while society might be better off, in the long run , as a result the affected individuals will probably not. We tend to generalize from a single historical example, the industrial revolution and, more specifically, the automatic loom, and in that case the displaced workers ended up doing worse. Better jobs and opportunities only got created later.

The other problem is, of course, is that all the historical examples (the data) are too few to generalize from while we do see how these examples are different from each other. As technological evolution progresses, automation gets more and more sophisticated, it can replace jobs that require more and more skills and talent. In other words, jobs that fewer and fewer people were able to do in the first place. This means that the bar for successfully competing in the labor market gets higher and higher and it will get to a point where a substantial number of people will just be plain uncompetitive for any job.

Or, at least that was one of the morels until LLMs were invented. (Mostly everyone thought that automation would take over the opportunities from the bottom up in general.) Now it seems that indeed white collar jobs are more in danger for now. But I digress.

The point here is that past examples are false analogies because AI (and I moslty mean future AI) is funcamentally different from past inventions. It's capabilities seem to improve quickly but we're mostly stuck with what evolution gave us. (We, as a species, are evolving but it's very slow compared to the rate of technological evolution and also we, as individuals, are stuck with whatever we were born with.)

I think the other thing people miss is the impact of our existing infrastructure on the speed at which these new technologies can be deployed.

Society had a lot of time to get used to the printing press, the advances of the Industrial Revolution and the internet. This is because the knowledge had to spread, and it's also because a ton of equipment had to be manufactured and/or shipped all over the world. We had to make printing presses, design and build factories, and get a critical mass of people internet-capable computers.

AI is fundamentally different, in that the knowledge of AI can spread instantly because of the internet and because the vast majority of the world already has access to all of the hardware they need to access the most powerful AI models.

Soon we'll have humanoid robots coming, and while they obviously have to be built, we are much more capable now than we were 50 years ago at building giant factories. We also have an efficient system of capital allocation that means that as soon as someone demonstrates a generally useful humanoid robot and only needs to scale production, they'll have access to basically infinite investor money.

I don't speak for the parent, but what they said seems true - Henry Hazlitt covers this phenomenon pretty well if you are ever interested. Your two points I think are also true. It won't be nice to everyone... Such is life. That being said, my practical mind is telling me to get ahead of it, whether that be learning new skills or whatever it takes to stay competitive. If that means picking another industry/profession entirely, so be it. You do what you gotta do.

The other problem with the excavator argument is that all that amazing productivity isn't being pulled from thin air by cleverness -- it's burning (limited, polluting) fossilized solar power from a million years ago. We haven't avoided all the work of moving the dirt around, but only transferred the burden from ourselves and our horses to our unsustainable energy sector. AI (and all software, really) is similar in that it tries to do the same to intellectual activities: instead of requiring a cheese sandwich and an afternoon, some tasks can be instead be done with a few cents worth of electricity and a few hundred milliseconds, but I still eat the cheese sandwich for lunch, so in the final analysis we've saved time but no other resource.

We of course wouldn't have to make this explicit calculation if we could incorporate all this knowledge about fossil fuels directly into the prices of goods and services, but this is very difficult thing to do, and so far nobody has managed to do it in a global way.

It may still make material sense to use ChatGPT to create slides for middle management meetings, but that is not at all certain in a world with a significant price on emissions (though, to be fair, almost no human activity from the past fifty years stands up to this test either).

IIRC, Microsoft, which is hosting OpenAI, has already their server farms on carbon-neutral electricity, and is heading towards full carbon neutrality on the lifecycle of their server farms.

So doing stuff yourself is less carbon efficient than letting ChatGPT do its job.

As for calculating co2 pollution into the prices - we're slowly doing that, e.g. EU is setting up its carbon tax that applies to companies abroad.

The issue is that if we were to instantly include true costs of carbon removal into everything, the economy might collapse at worst, and at the least poor people might not afford food, heating nor other basic necessities any more. It will take time to do it sensibly.

I'm skeptical that industrial civilization can exist at all (at least on anything like a billions-of-people scale) with priced-in emissions, but I guess we'll see. Widespread famine and suffering are in store one way or the other (either because of climate change, or because of what we will need to do to fight climate change).

So far we’ve been exceeding the predictions for switching to carbon neutral economy, so I wouldn’t be too sure of that.

I share a similar intuition, but am skeptical that my imagination is in the right ballpark of what it will look like 15 years hence.

What do you think programming will be like in 15 years and where is the high-value work by human programmers?

Same as looking back 15-20 years ago from now, though.

Very few jobs now where you put together basic webpages with HTML and CSS (Frontpage, then Wix/Wordpress etc replaced you). Very few jobs where you spend 100% of your time dealing with database backups and replication and managing the hardware (the cloud replaced you). Very few jobs where you spend all your time planning hardware capacity and physically inserting hard disks into racks (the cloud replaced you, too).

I think AI will shift the value from those who know how to program toward those who know which programs are most useful to write. In other words, we’ll all become product engineers.

>I think the internet and the open source movement had a similar effect, in that if you did not attempt a project that you had some small interest in, it would only be a matter of time before someone else did enough of a similar problem for you to reuse or repurpose their work, and this led to an explosion of (often useful, or at least usable) applications and libraries.

Being developing before when Mac had b&w screen (system 6?). Had so many good ideas just didn't work on them for whatever reason, and eventually someone did them. Maybe it is just tech people run into the same problem, or collective tech unconscious, the longer you have being around, eventually people in the industry will try to solve the problems. These occurrences goes to show me that there are really aren't many true original ideas out there, a lot of it comes down to implementation, PR, funding, geopolitics, your users and luck.

Reply on news.ycombinator.com