Since when did Claude Code get so risk averse?!

All these convos on whether an experience is nerfed would go away if more of this config was exposed and locked to versions.

I can see big companies wanting more predictability in this and insisting they have their own stack for these reasons. You can't be counting on a certain way of working and then have it change underneath you.

I get that AI models are non-deterministic, but I've started to see swings in behaviour that break my assumptions of how things work.

I think it would be helpful if AI companies were a little more explicit when they were modifying their models and infra. Changing the prompts in agent harnesses is also an issue. Feels like I'm working with a different models.

The agentic era is gonna be huge for devops and infra companies.

The need for virtualization, machine snapshots, infra as code, db cloning, you name it goes through the roof when you have a single human programmer managing even 5 agents working on a non-trivial system.

Claude was more concise previously. (Or at least it feels that way)

Also: who convinced Claude that answer questions with a 1000 word essay is the right move. It's like that friend who doesn't hit send while they respond and just dumps you with a full screen of text. This has also been getting worse of late.

I would love to see how the system prompt Claude Code uses evolves because I don't think the changes are always an improvement. Or maybe it's the full harness composition.

Things be weird. I like my robots a wee bit more predictable.

Woke up. Started work. Today's Claude is a different Claude than a few days ago.

I would really love a peek behind the scenes to know what changes when using Claude Code from having a highly productive Claude who gets my codebase and project to one that's doing the dumbest stuff.

Anything else is a recipe for headaches that waste time and avoidable.

It's way to easy to have db migration from one branch causing issues in another branch because both are trying to do things with the db that the other doesn't understand.

The longer I do this agentic programming thing the more I'm convinced that every agent needs its own box to live in.

If you're using a system that uses a database, using multiple agents with worktrees or separate checkouts do not ultimately solve the problem of colliding agents.

You need full isolation.

You don't have to manage releases. Everytime someone connects, they will get the latest tools.

Much better than having to manage API and CLI versions.

Having now built a CLI, a stdin MCP server, and a remote MCP server, I would say that if your MCP server doesn't need to do anything locally, go the distance.

Create the remote MCP server for this one reason:
No versions.

It's amazing what one guy with a clear vision can do.

I am that guy.

AI is an amazing paint brush and poor artist.
AI is an amazing programmer and poor system designer.

If you can get your thinking right, AI is a rocket shovel.

Thank you @jdxcode for mise, hk. 🙇
I appreciate all that you've brought to the world.

Even if AI could only fix my vim config and other setup, it would be worth it. Just unified my keymaps across Zed and neovim and boy is my muscle memory happy.

Those refactors you been putting off,
Those doc updates you been deferring,

time to enlist your favourite agent.

A finely manicured projects is within your reach.

AGENTS.md AGENTS.md is a simple, open format for guiding coding agents. Think of it as a README for agents.

We pack all sorts of workflow efficiencies into our dotfiles.
Agents can benefit from those tools too.

The question is how do we setup a dev experience that's reproducible and agent-friendly.

Same tools for humans and agents.
Clear description in the AGENTS.md of what exists

🤔

I remember when I used to do day long rebases.
Boy am I glad those days are over.

It feels like I have a tutor that's always teaching me new things.
It makes upcoming tasks easier because I'm primed with the key concerns.

I think @mitchellh's advice to always have an agent running doing research on your next task is a great idea. I've been doing it and it's had a couple interesting effects.

New Claude verson. Back to it thinking it knows what I want my PRs to look like more than I and straight.

@bcherny @_catwu did the env variable to turn off the git prompt get removed? I have it on and everything was 10/10 for a few releases.

If you're tightly coupled to a big platform like Shopify and they have a version release cycle and you have an API that needs versions, use the same one. It'll save you the headache of reasoning about what's valid when.

Did a demo today of a tool using a first-of-its-kind data store and seeing the agent make use of the data was really cool! 🤖

I create disposable tools to help me solve a problem and I've started leaning more and more on the @vuejs and @vite_js ecosystem.

The agents is able to build complex things without a ton of setup or ceremony. React would be fine too. The key is its a highly reactive client side only framework.

--dangerously-skip-permissions is the only way to live.

Why did it take me almost a year to adopt it? 🤦

Is it me or is GitHub degrading by the day?