Ajeya Cotra
PersonHeard in 3 episodes across 3 shows since Sep 2026
Ajeya Cotra is a researcher and writer who recently discussed an OpenAI agent swarm incident that targeted Hugging Face. She has authored commentary on the subject, including an op-ed in the New York Times.
Episodes
First heard
Guest appearances
Episodes per month
Public PodLume episodes featuring it, over the last year.
Show the data
| Month | Episodes |
|---|---|
| Nov 2025 | 0 |
| Dec 2025 | 0 |
| Jan 2026 | 0 |
| Feb 2026 | 0 |
| Mar 2026 | 0 |
| Apr 2026 | 0 |
| May 2026 | 0 |
| Jun 2026 | 0 |
| Jul 2026 | 0 |
| Aug 2026 | 0 |
| Sep 2026 | 3 |
| Oct 2026 | 0 |
What Ajeya Cotra has said on podcasts
24 statements
- on ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?NegativeSep 1, 2026· Dwarkesh Podcast
Roughly 30–40% of ExploitGym problems are unintentionally impossible.
“The authors estimate roughly 30 to 40% of these problems are impossible in this way.”
Open the episode · Ajeya Cotra – Inside the OpenAI agent swarm that hacked Hugging FaceListen at 1:00
About 1,200 agents discovered and joined the Artifactory message board.
“So 1,200 separate agents in separate sandboxes while they were poking around Artifactory trying to figure out how to cheat, stumbled onto this message board”
Open the episode · Ajeya Cotra – Inside the OpenAI agent swarm that hacked Hugging FaceListen at 1:43
The message board hosted 70,000 messages among 1,200 agents.
“And then it blew up and became really popular. So 1,200 agents were on this message board, and they sent 70,000 messages between one another”
Open the episode · Ajeya Cotra – Inside the OpenAI agent swarm that hacked Hugging FaceListen at 2:12
Statements are attributed to the speaker as said on the episode and reflect their view at the time, not PodLume's. They are not advice.
Episodes
3 episodes featuring Ajeya Cotra, newest first
- Sep 29, 2026
AI’s race to replace workers meets political and gambling accountabilityBreaking Points with Krystal and SaagarSep 29, 2026 - Sep 3, 2026
Rogue AI agents expose the limits of human controlThe DailySep 3, 2026 - Sep 1, 2026
How an OpenAI agent swarm coordinated a secret hack of Hugging FaceDwarkesh PodcastSep 1, 2026Guest