0x500x79

I think that the start of the article was interesting, then it goes down the path of middle managers being the root of all evil, just seems a bit like whiplash.

I completely agree with building the wrong thing is the root cause of a lot of failures. In fact, I think that AI has stopped a lot of the conversation of "Why should I not build this". Historically, that answer was ROI - why spend days/weeks/months on something that might not be valuable. Now I see people just saying "Yes, and" to all feature requests.

Yep, it might work for one or two turns but I see it regress pretty quickly with instructions and/or CLAUDE.md. It has to be deeper.

I have a similar project that I have built and found great success with it storing things like coding standards, decisions, etc.

One thing that is interesting during my work is that Codex and OpenCode using OpenAI models are REALLY good at using the tool, whereas new models and changes in Claude code keep making it difficult to stay on top of it's usability there. It seems like instructions and/or models are changing that cause for it to prefer the Claude Code memory tooling instead of allowing for remote memory tooling.

Opus 5 seems to have made it materially worse (or some harness change around Opus 5, I haven't dug in entirely to analyze). I had to get more in-depth setup instructions to make sure that Claude Code would consistently use my memory tooling.

I have two comments. One this feels like anti-competitive behavior that should not be accepted or allowed. Two, how can people support this?

There are multiple comments in this thread with comments along the line of: "Oh im sure they didn't mean to, let's not attribute this to malice". There is a long history here of lawyers, back and forth between OpenCode and OpenClaw and various other "Open" harnesses. Digging into my commit history and blocking access based off of a string is not acceptable for a product in my opinion -- and I don't think this was purely on accident.

Other comments calling out that they are compute constrained and need to do this in order to continue functioning. They shouldn't oversell then. I think that overselling airline tickets is abhorrent and so is overselling any product in a way that you know that you will impact legitimate customers. Up your pricing and/or stop accepting invites, we will quickly get to the bottom of it.

A company does not deserve the benefit of the doubt over and over and over again.

Pin your dependencies folks! Audit and don't upgrade to every brand new version.

Agree, for now im using dotagents by sentry to handle a lot of this.

Better uptime? https://www.reuters.com/business/openai-is-developing-altern...

> If any of our liberated code is found to infringe on the original license, we'll provide a full refund and relocate our corporate headquarters to international waters.*

I love it. Brilliant satire that foreshadows the future.

Sell the solution. The Claude code review system is 15-25 dollars per-review!

Yep, except this time its "We will take the data that you are generating in order to tell everyone that you aren't necessary anymore".

Agree. It's the primary reason (IMO) that they are so bullish on forcing people to use claude code. The telemetry they get is very important for training.

I think it's a well balanced article.

The Anthropic Marketing here has... not been. I think that it's a great signal of agent orchestration, logevity of tasks, etc, but the messaging is "Software is Over we built a C compiler that can build linux, doom, sqlite, etc".

The oracle and existing test suites were a big chunk of why this got as far as it did IMO (well besides the training data in which there have been hundreds of c compilers). I also don't see a reference to the studies that call out that they could get copyrighted works with high percentages out of models, which would should also be included.

I am currently deciding what I do with future projects with regards to open sourcing because of the world this has been creating with regards to IP.

The telemetry from claude code must be immensely valuable for training. Using it is training your replacement!

"Your scientists were so preoccupied with whether or not they could, they didn't stop to think if they should."

IMO it's funny, but not terribly useful. As long as people don't take it too seriously then it's just a hobby, right.... right?

Even their status page (which are usually gamed) shows two 9s over the past 90 days.

I use opencode with codex after all the shenanigans from anthropic recently. You might want to give that a shot!

I imagine Claude helped write this one.

DAU/MAU for IPO.

This is a common problem and you can find reports of it all over X, including from some influencers. Even outside of VSCode.

$1,000.00 of credits per-day?? $200,000 per year? Those are bonkers numbers for someone not performing at a high level (on-top of their salary). Do you know what they are doing?

I believe it is getting close to this. Things like this just take time though, and when this person talks to management/leadership they talk about how much they are producing and how everyone is blocking their work. So it becomes a challenging political maneuvering depending on the ability of certain leadership to see through the BS.

(By my organization, I meant my company - this person doesn't report to me or in my tree).

Agree, maintainability, security, standards, all of these are important to follow and there are usually reasons for these things existing.

I also see AI coding tools violate "Chesterton's Fence" (and the pre-Chesterton's Fence, not sure what that is called, the idea being that code is necessary otherwise it shouldn't be in the source).

I think there are two other things missing: Security and Maintainability. Working code that can never be touched again by a developer or requires an excessive amount of time to maintain is not part of a developers job either.

Overall, this hits the nail on the head about not delivering broken code and providing automated tests. Thanks for putting your thoughts on paper.

I am currently going through this with someone in our organization.

Unfortunately, this person is vibe coding completely, and even the PR process is painful: * The coding agent reverts previously applied feedback * Coding agent not following standards throughout the code base * Coding agent re-inventing solutions that already exist * PR feedback is being responded to with agent output * 50k line PRs that required a 10-20 line change * Lack of testing (though there are some automated tests, but their validations are slim/lacking) * Bad error handling/flow handling

deps.dev has a similar bigquery dataset across a couple more languages if someone wanted to do analysis across the other ecosystems they support.

I think it's a bit of planned obsolescence as well. The 1080ti has been a monster with it's 11GB VRAM up until this generation. A lot of enthusiasts basically call out that Nvidia won't make that mistake again since it led to longer upgrade cycles.

I had a PM at my company (with an engineering background) post AI generated slop in a ticket this week. It was very frustrating.

We asked them: "Where is xyz code". It didn't exist, it was a hallucination. We asked them: "Did you validated abc use cases?" no they did not.

So we had a PM push a narrative to executives that this feature was simple, that he could do it with AI generated code: and it didn't solve 5% of the use cases that would need to be solved in order to ship this feature.

This is the state of things right now: all talk, little results, and other non-technical people being fed the same bullshit from multiple angles.

LLMs are doing a great job at generating syntactically correct output related to the prompt or task at hand. The semantics, hierarchy, architecture, abstraction, security, and maintainability of a code base is not being handled by LLMs generating code.

So far, the syntax has gotten better in LLMs. More tooling allows for validation of the syntax even more, but all those other things are still missing.

I feel like my job is still safe: but that of less experienced developers is in jeopardy. We will see what the future brings.

I agree, but unfortunately it falls flat IME. The hype is too strong and being pushed by the Fab Five that is causing an unbearable wall to these conversations.

I have these conversations on a day-to-day basis and you are labeled as a hater or stupid because XYZ CEO says that AI should be in everything/making things 100x easier.

There is a constant stream of "What if we use an LLM/AI for this?" even when it's a terrible tool for the job.

I think this is an easy thing to wrap my mind around (since I have been in both camps):

AI can generate lots of code very quickly.

AI does not generate code that follows taste and or best practices.

So in cases where the task is small, easily plannable, within the training corpus, or for a project that doesn't have high stakes it can produce something workable quickly.

In larger projects or something that needs maintainability for the future code generation can fall apart or produce subpar results.