HackerTrans
トップ新着トレンドコメント過去質問紹介求人

chris_st

1,597 カルマ登録 11 年前

投稿

The Agent Operating System

librefang.ai
3 ポイント·投稿者 chris_st·3 日前·0 コメント

コメント

chris_st
·3 日前·議論
FWIW, Cognition has all the Sonnet/Opus/Fable models, and all the GPT ones, as well as GLM, Kimi, and Gemini.
chris_st
·先月·議論
What "non-house" harnesses have you found to work best?
chris_st
·先月·議論
Interesting to see (roughly!) what percent of each car is engine.
chris_st
·先月·議論
I have this setup, roughly, with UTM rather than orbstack. I think I have it set up safely, curious how you see it has the wrong permissions?
chris_st
·2 か月前·議論
Another way I'm "going slower" is to have the AI implement individual sub-steps of the current task, and review each one. It's slower than having it yolo out the whole thing, but it's much smaller incremental bits to review, so my brain doesn't glaze over in a huge review, like I had if I had it do the whole task.

I'm following an Ideas -> PRD -> Issues -> Tasks methodology, where each task has a bunch of sub-tasks. I have it just do one (or a few, I'm having it do Red/Green/Refactor as separate sub-steps, so I review the Red case, and then once that's good, do the Green and Refactor steps, and review those).
chris_st
·2 か月前·議論
Yup, just like people!
chris_st
·2 か月前·議論
Good!
chris_st
·2 か月前·議論
Nope, not better quality if you don't like the smell of cigarettes.
chris_st
·2 か月前·議論
Please add support for the Windsurf editor as well. Thanks!
chris_st
·2 か月前·議論
Awesome, stealing that!
chris_st
·2 か月前·議論
And they're clearly marked as `unsafe`, so easy to find, which gives them a nice list of issues to address.
chris_st
·2 か月前·議論
I asked Claude to tell me why something was implemented the way it was, and got an excellent response. One data point, would love to hear more examples.
chris_st
·2 か月前·議論
...it came as a surprise that [leaving a Petri dish out with a window open] would end up with interesting [molds] (called [penicillin]). _It was not planned at all_.
chris_st
·3 か月前·議論
Well, to be fair, people cheat by remembering what they did last time. I think the idea here is to run the models from a "clean slate" and see how often they succeed/fail.

They are, like people, non-deterministic, so giving them several "fair" trials makes sense to me.
chris_st
·3 か月前·議論
Possibly because they just haven't been able to manufacture enough of them yet to be a viable business to others? They're fighting everyone else for foundry space and time.
chris_st
·3 か月前·議論
But it's pretty cool that LLM bug hunting is pretty cheap... the 1-person projects can do it themselves, don't have to contract out to some huge security company.
chris_st
·3 か月前·議論
Well, maybe not... see Simon Willison's ongoing reporting [0] on all the bug reports for `curl` people are finding with LLMs.

Interesting to see them go from "DON'T GIVE US AI SLOP!" to "Wow, lots of actual bugs found, including [ed: at least one] bug found by two people!"

[0]: https://simonwillison.net/search/?q=curl
chris_st
·3 か月前·議論
From the article:

> As we noted at its September beta release, a windowed version of Tailscale’s macOS app doesn’t replace the menu bar app, but runs alongside it. It can be pulled up from the Dock or a Spotlight search, and makes a lot of Tailscale data and features more accessible.
chris_st
·3 か月前·議論
Seconding Maple Mono - it's very nice.
chris_st
·5 か月前·議論
Just out of curiosity, which version of Claude?