Cord: Coordinating Trees of AI Agents
1–10 of 93 posts
Re: Cord: Coordinating Trees of AI Agents
#2[flagged]
Re: Cord: Coordinating Trees of AI Agents
#3[flagged]
Re: Cord: Coordinating Trees of AI Agents
#4[flagged]
Would those agents happened to be named frk_ai_8b2e and that platform news.ycombinator.com?
Re: Cord: Coordinating Trees of AI Agents
#5Re: Cord: Coordinating Trees of AI Agents
#6I wonder if the “spawn” API is ever preferable over “fork”. Do we really want to remove context if we can help it? There will certainly be situations where we have to, but then what you want is good compaction for the subagent. “Clean-slate” compaction seems like it would always be suboptimal.
Re: Cord: Coordinating Trees of AI Agents
#7Feels very AI written in a way that makes it annoying to read with all the repetitive short sentences.
Neat concept though, would be cool to see some tests of performance on some tasks.
Re: Cord: Coordinating Trees of AI Agents
#8Not exactly a surprise Claude did this out of the box with minimal prompting considering they’ve presumably been RLing the hell out of it for agent teams: https://code.claude.com/docs/en/agent-teams
Re: Cord: Coordinating Trees of AI Agents
#9all of these frameworks will go away once the model gets really smart. it will just be tool search, tools, and the model
in the short run, ive found the open ai agents one to be the best
Re: Cord: Coordinating Trees of AI Agents
#10Not to be confused with:
cord - The #1 AI-Powered Job Search Platform for people in tech