csar

The Chili Peppers long ago settled the ethics of coyote culling, but your attitude is cavalier and thoughtless.

For those of us living in suburbs, young children running just a few steps ahead (e.g. from the house to the other end of the driveway) can be in significant danger from coyotes.

Your hyperbole and cursing are not a great match for this forum and you should reconsider them or leave.

Yeah I started in 98 or so and stopped in 2009. I should check back in.

For new-ish projects it should give you some crazy speed up out of the box.

For large codebases (my own has 500k lines and my company has a few tens of millions) you need something better like RPI.

If nothing else just being able to understand code questions basically instantly should give you a large speed up, even without any fancy stuff.

It’s told to only use it if relevant because most people write bad ones. Someone should write a tool to assess CLAUDE.md quality.

Claude Code is better out of the box, so all that other stuff is orthogonal or optional. If you eg want to give your agent access to your company’s Notion docs you need a skill.

You should never let context get that high unless you’re doing really basic things. Somewhere 40-60% is generally the time to start thinking about exits for tougher tasks. Get out in the 60s.

I understand. My point is that the personas are generally not a good idea and that there are much simpler and more predictable ways of getting better results.

Getting feedback on a plan or implementation is valuable because you get a fresh set of eyes. Using multiple models may help though it always feels a bit silly to me (if nothing else you’re increasing non-determinism because you know have to understand 2 LLM’s quirks).

But the “playing house” approach of experts is somewhere between pointless and actively harmful. It was all the rage in June and I thought people abandoned that later in the summer.

If you want the model to eg review code instead of fixing things, or document code without suggesting improvements (for writing docs), that’s useful. But there’s. I need for all these personas.

Love the throwbacks.

I wasted a few minutes earlier today trying to find the original website for the Cocoa class that Tristan helped set up a few years before this one got started.

Me: “This link can’t possibly be about what I think it might be about.” Me, seconds later: “Yes it is!!”

If you're getting AI slop you're doing it wrong. You should be getting high quality code. Of course that's easier said than done, but AI slop is a sign that things have gone off the rails.

I’m curious how you think this compares to the Research -> Plan -> Implement method and prompts from the “Advanced Context Engineering from Agents” video when it comes to actual coding performance on large codebases. I think picking up skills is useful for broadening agents abilities, but I’m not sure I’d that’s the right thing for actual development.

The packaged collection is very cool and so is the idea of automatically adding new abilities, but I’m not fully convinced that this concept of skills is that much better than having custom commands+sub-agents. I’ll have to play around with it these next few days and compare.

OP is one of the co-creators of Django (for which I am eternally grateful, having built my first company on top of it) and one of the most prolific writers in the space. I also happen to strongly agree with his assessment, though as he said getting that amount of value out of current tools is real work.

This is exactly right.

“70% of tests pass. This codebase is ready for production!”