Are there good guides about how to write Agents or good repos with examples? Also, are there big differences between how you would write one in Codex cli vs Claude code? Can there be run on it interchangeably?
A few random notes from Claude coding quite a bit last few weeks
511–520 of 870 posts
Re: A few random notes from Claude coding quite a bit last few weeks
#512Earlier quoted context omitted.
Have you an example of getting a coding chatbot to do exactly what you want?
https://gisthost.github.io/?a41ce6304367e2ced59cd237c576b817... - which built https://github.com/datasette/datasette-transactions exactly the way I wanted it to be built
The problem with replying to the proof-demanders is that they'll always pick it apart and find some reason it doesn't fit their definition. You must be familiar with that at this point.
Re: A few random notes from Claude coding quite a bit last few weeks
#513Thank you for the really excellent summation. I echo your thought 1 to 1. I have found it more difficult to learn new languages or coding skills, because I am no longer forced to go through the painful slow grind of learning.
Does one ever still need to learn new languages or coding skills if an AI will be able to do it?
Re: A few random notes from Claude coding quite a bit last few weeks
#514> LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building. I’ve always said I’m a builder even though I’ve also enjoyed programming (but for an outcome, never for the sake of the code) This perfectly sums up what I’ve been observing between people like me (builders) who are ecstatic about this new world and programmers who talk about the craft of programming…
There's more to it than just coding Vs building though.
For a long time in my career now I've been in a situation where I'd be able to build more if I was willing to abstract myself and become a slide-merchant/coalition-builder. I don't want to do this though.
Yet, I'm still quite an enthusiastic vibe-coder.
I think it's less about coding Vs building and more about tolerance for abstraction and politics. And I don't think there are that many people who are so intolerant of abstraction that they won't let agents write a bunch of code for them.
Re: A few random notes from Claude coding quite a bit last few weeks
#515I worry about the "brain atrophy" part, as I've felt this too. And not just atrophy, but even moreso I think it's evolving into "complacency". Like there have been multiple times now where I wanted the code to look a certain way, but it kept pulling back to the way it wanted to do things. Like if I had stated certain design goals recently it would adhere to them, but after a few iterations it would forget again and g…
I think I should write more about but I have been feeling very similar. I've been recently exploring using claude code/codex recently as the "default", so I've decided to implement a side project. My gripe with AI tools in the past is that the kind of work I do is large and complex and with previous models it just wasn't efficient to either provide enough context or deal with context rot when working on a large appli…
I ran into similar issues with context rot on a larger backend project recently. I ended up writing a tool that parses the AST to strip out function bodies and only feeds the relevant signatures and type definitions into the prompt.
It cuts down the input tokens significantly which is nice for the monthly bill, but I found the main benefit is that it actually stops the model from getting distracted by existing implementation details. It feels a bit like overengineering but it makes reasoning about the system architecture much more reliable when you don't have to dump the whole codebase into the context window.
Re: A few random notes from Claude coding quite a bit last few weeks
#516> It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. This is true... Equally I've seen it dive into a rabbit hole, make…
I don't understand why anyone finds it interesting that a machine, or chatbot, never tires or gets demoralized. You have to anthromorphize the LLM before you can even think of those possibilities. A tractor never tires or gets demoralized either, because it can't. Chatbots don't "dive into a rabbit hole ... and then keep digging" because they have superhuman tenacity, they do it because that's what software does. If I ask my laptop to compute the millionth Fibonacci number it doesn't sigh and complain, and I don't think it shows any special qualities unless I compare it to a person given the same job.
Re: A few random notes from Claude coding quite a bit last few weeks
#517Earlier quoted context omitted.
I’d push back on this framing a bit. There's a subtle ageism baked into the assumption that someone who stepped away from day-to-day coding has "ancient skills" worth mocking. Yes, specific frameworks and tooling knowledge atrophy without use, and that’s true for anyone at any career stage. A developer who spent three years exclusively in React would be rusty on backend patterns too. But you’re conflating current too…
This has nothing to do about ageism. This applies to any person of any age who has ego big enough to think that their knowledge of industry is relevant after they take prolonged break and be socially inept enough to brag about how they are still "in". I don't disagree with your point about fundamentals, but in an industry where there seems to be new JS framework any time somebody sneezes - latest tools are very much…
I beg to differ. I started with C in the 90s, then C# in '05, then PHP in '12, then Go in '21. The things I learned in C still apply to Go, C#, and PHP. And I even started contributing to open source C projects in '24 ... all my skills and knowledge were still relevant. This sounds exactly like ageism to me, but I clearly have a different perspective than you.
Re: A few random notes from Claude coding quite a bit last few weeks
#518Earlier quoted context omitted.
Why not? You can select Opus 4.5, Gemini 3 Pro, and others.
Claude Code is a CLI tool which means it can do complete projects in a single command. Also has fantastic tools for scaffolding and harnessing the code. You can define everything from your coding style to specific instructions for designing frontpages, integrating payments, etc. It's not about the model. It's about the harness
Huh? There is nothing stopping copilot from doing an entire project in one go.
Ive done it 10s of times.
Re: A few random notes from Claude coding quite a bit last few weeks
#519I keep thinking about the TechnoCore from Dan Simmons' Hyperion, where the AIs were serving humans but secretly that was a parasitic relation, where they've been secretly using human brains as distributed processing nodes, essentially harvesting humanity's neural activity for their own computational needs without anyone's knowledge.
I know this is SF, but to me working with those LLMs feels more and more like that, and the atrophy part is real. Not that the model is literally using our brains as compute, but the relationship can become lopsided.
Re: A few random notes from Claude coding quite a bit last few weeks
#520I worry about the "brain atrophy" part, as I've felt this too. And not just atrophy, but even moreso I think it's evolving into "complacency". Like there have been multiple times now where I wanted the code to look a certain way, but it kept pulling back to the way it wanted to do things. Like if I had stated certain design goals recently it would adhere to them, but after a few iterations it would forget again and g…
My advice: keep it on a tight leash.
In the happy case where I have a good idea of the changes necessary, I will ask it to do small things, step by step, and examine what it does and commit.
In the unhappy case where one is faced with a massive codebase and no idea where to start, I find asking it to just “do the thing” generates slop, but enough for me to use as inspiration for the above.