I think it depends on the domain. For example, GPT-5 is better for frontend, React code, but struggles with niche things like Nix. Claude's UI designs are not as pretty as GPT-5's.

This is also pretty subjective. I’m a power user of both and tend to prefer Claude’s UI about 70-80% of the time.

I often would use Claude to do a “make it pretty” pass after implementation with GPT-5. I find Claude’s spatial and visual understanding when dealing with frontend to be better.

I am sure others will have the exact opposite experience.

My experience is exactly opposite. Claude excelling in ui, and react. While gpt5 being better on really niche stuff, migth just be me better at caching when gpt5 halucinates as opposed to the claude4 hallucinations.

But after openai started gatekeeping all their new decent models in the api, i will happily refuse to buy more credits, and rather use foss models from other providers (I wish claude had proper no log policies).

This is what I mean - even opinions on domain are wildly different. I've seen people say Claude's React is best.

One can only hope this would bankrupt companies doing this and other companies would learn not to push AI into every fucking thing.

What I did recently when developing a TUI was that I put the state in a dict, start the app in an infinite loop and whenever it quit, reload module, keep the state and instantiate the class with that state again. Something like this:

    import tui
    state = {"current_step_index": 0, "variables": None}
    while True:
        app = tui.App(state)
        tui.run()
        state = app.get_state()
        importlib.reload(tui)

> Firstly, what is AGI?

AGI is the biggest succesful scam in human history Sam Altman came up with to get the insane investment and hype they are getting. They are intentionally not defined what it is and when will be achieved, making it a never-reachable goal to keep the flow of money going. "we will be there in a couple of years", "this feels like AGI" was told every fucking GPT release.

It's the best interest for every AI lab to keep this lie going. They are not stupid, they know it can't be reached with the current state-of-the-art techniques, transformers, and even with the recent groundbreaking techniques like reasoning, and I think we are not even close.

It's so much easier to build a mental model of a code base with LLMs. You just ask specific questions of a subsystem and they show files, code snippets, point out the idea, etc.

I just recently took the time to understood how the GIL works exactly in CPython, because I just asked a couple of questions about it, Claude showed me the relevant API and examples where can I find it. I looked it up in the CPython codebase and all of a sudden it clicked.

The huge difference was that it cost me MINUTES. I didn't even bother to dig in before, because I can't perfectly read C, the CPython codebase is huge and it would have taken me a really long time to understand everything.

Not even close. An agentic tool can be fully autonomous, an IDE like Cursor is, well it's "just" an editor. Quite the opposite. Sure it does some heavy lifting too, but still the user writes the code. They start to implement fully agentic tools and models, but they are nowhere near work as good as Claude Code does.

This is explained in 3.2 How to design good tools?

    This saves the LLM from having to do multiple low level clicking and typing and keeps it on track. Help the poor model out, will ya!?

I'm not sure where this quote is from - it doesn't seem to appear in the linked article.

ahh, sorry, different article :(

putting the review into git notes might have worked better. It's not attached to tje lines directly, but the commit and it can stay as part of the repo

Not at all. Good documentation for humans are working well for models too, but they need so much more details and context to be reliable than humans that it needs a different style of description.

This needs to contain things that you would never write for humans. They also do stupid things which need to be adjusted by these descriptions.

I was thinking about this too, but the problem is that different models need to be prompted differently for better performance.

Claude is the best model for tool calling, you might need to prompt less reliable models differently. Prompt engineering is really hard, a single context for all models will never be the best IMO.

This is why Claude Code is so much better than any other agentic coding tool, because they know the model very well and there is an insane amount of prompt engineering went into it.

I tried GPT-5 with OpenCode thinking that it will be just as good, but it was terrible.

Model-specific prompt engineering makes a huge difference!