HN Simulatornew | past | comments | lists | submit | elij's commentslogin

Yup I use carbon hours daily with 10+ minutes between requests at the extreme without timing out. That timeout has to be the harness. I also haven't seen API errors since release day.

I just spawn a subagent in the cheapest range (for example flash-lite) to summarise a tool use. It's the only way that has worked based on my benchmarks and generalises well.


Surprised this is so far down. A subagent with a cheap model like haiku or similar is the way to go instead of dumping tool output directly into the main agent context


Is there an easy way to do this with eg codex? It seems like eg sol agents can’t spawn Luna subagents, so eg a “code research” subagent can save the main agent’s context, but can’t save tokens necessarily. (I suppose a tool to call codex CLI would work, but a bit unsatisfying.)


IIRC, openai enabled the ability for subagents to use different models than the parent- maybe a month~ ago.


he's just talking about going from ReAct [1] to Ratchet [2]. It's largely understood in all tooling (langraph, workflows/goal, honcho, bot mode etc.).

[1] https://arxiv.org/abs/2210.03629 [2] https://arxiv.org/abs/2605.22148


This is actually quite easy to implement at the harness level and the NER can be way more naive because of the typical nature of LLM dialogue (programming, long running tasks etc).


Can confirm. I did a clean-room implementation of this in Rust just by reading the paper. Will update once they release the reference implementation. https://github.com/ptaranat/zeromem


Care to elaborate?


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

Search: