Hacker Newsnew | past | comments | ask | show | jobs | submit | ssk42's commentslogin

/model then roles and also /agents for when a model chooses to delegate out sub agents

My gut instinct is that this is about when all of their on prem servers were EOL and their /public cloud solution was required. This must have had something to do with that

My gut instinct is that this is about Dreamforce with the rickshaws and whatnot

That’s what my KimiClaw has literally been doing


What is your favorite harness for the open weights?


We built our own and aren't done open sourcing it but before that I got to a really good place with opencode plus some custom agents, pi family is good too although I haven't used it as much. We made an agent to design a spec, one to implement by dispatching subagents, one to validate against the plan, things like that. All of this helps claude/gpt too IME. For open models it has helped them stay out of loops (e.g. Kimi's but WAIT) and for frontier it helps them stay on task and not invent bloated patterns


pi is great for learning, oh-my-pi has all the nice things included that I've built fory pi previously.


pi-mono


What is pi-mono ? (I heard about pi)


If I recall correctly, in their pivot to Codex they took a sizable amount of compute away from ChatGPT


I’m sorry but in this day and age, why would you not use AI with safeguards? With giving it the proper context and best practices you’re looking for. These are all very solved in Claude and any agentic system. Are you saying that you don’t? This just feels insulting to those of us who do care about code but do love Claude


Can you defend that though? Does living mean needing cells? Does it mean possessing the ability to think and reason? Is Claude thinking and reasoning?


Fun to see you not on tildes.

Setting up a clean room is one of the only ways to do Evals on agentic harnesses. Especially prevalent with Windsurf which doesn’t have an easy CLI start.

So how? The easiest answer when allowed is docker. Literally new image per prompt. There’s also flags with Claude to not use memory and from there you can use -p to have it just be like a normal cli tool. Windsurf requires manual effort of starting it up in a new dir.


Sounds interesting, but I'm not quite getting the relevance for people writing code with an agent. Should I be doing evals?


Well I mean yes. I think people ought be aware for how the harnesses compare for their stacks. But clean room applies for this RGR situation too


you are replying to a bot, that's why.


What


ClawdBots can now more easily interact with the Internet than regular agents, so you wind up with Moltbook leaking


The biggest clue I’ve seen is someone using it to do cold calls on websites. Claw searches for shoddy-looking construction sites, makes a better version on Vercel, and sends out a pitch.


Are we visiting the same sites/talking to same people? Because I heard about this “use case” couple of days ago.


Probably. It was on my tiktok FYP


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: