Episode
"Swarm Scaling" by Toby_Ord
- Published
- Sep 22, 2026
- Duration seconds
- 959
- Processing state
not_requested
Actions
POST https://stenobird.com/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/swarm-scaling-by-toby-ord/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/lesswrong-curated-popular-5643401/swarm-scaling-by-toby-ord.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
Just how powerful are large swarms of AI agents? And how do their powers scale as more and more agents are added to the swarm? We’ve seen two large and extremely capable swarms from OpenAI in the last few months: 1,200 agents were being evaluated separately, but found a way to illicitly set up a message board and coordinate as a swarm. In order to cheat on their tests, they developed advanced techniques to prevent their actions being logged by OpenAI and 700 of them launched a sophistic...