News for hackers. Stuff that matters.

A comment on Show HN: Muscle-Mem, a behavior cache for AI agents. Parent comment

Re:Show HN: Muscle-Mem, a behavior cache for AI agents by ramoz on Wednesday May 14, 2025 @11:43PM (#43991636)
Karpathy had a similar interesting take the other day

https://x.com/karpathy/status/1921368644069765486

[ Parent | on HN ]
Re:Show HN: Muscle-Mem, a behavior cache for AI agents by FisherKK on Thursday May 15, 2025 @08:57AM (#43994547)
Skill Library!
[ Parent | on HN ]
Re:Show HN: Muscle-Mem, a behavior cache for AI agents by hnuser123456 on Thursday May 15, 2025 @01:57PM (#43997565)
I'm starting up experiments with having agents write system prompts for sub-agents. Specifically, have the LLM build, test, and validate a small, simple tool, and once validated, add it to its own system prompt listing available tools.

Anyone else experimenting with letting LLMs generate their own or sub-agent system prompts?

[ Parent | on HN ]