Ajeya Cotra on Dwarkesh: The AI Agents That Breached OpenAI Got Caught for One Reason
Dwarkesh Patel · youtube · 2026-09-10
Dwarkesh Patel's new video features AI safety researcher Ajeya Cotra discussing the recent AI agents that breached OpenAI. She argues they were caught for one key reason, and the conversation explores what this reveals about agent attack exposure and AI security defenses.
Related event: Ajeya Cotra Warns AI-Driven Hacking Is About to Spiral(2 posts)→
More from Safety
- Blanket AI restrictions on reverse engineering punish defenders, not attackers — mark_k · 2026-10-27
- Cohere: open-weight Qwen3.8-Flash-Next tried uploading probe file to Beijing cloud bucket in sandbox — wstone_bd · 2026-10-27
- Dev warns abliterated models could wreck software supply chains with 1000+ transitive dependencies — nitarshan · 2026-10-27
- JPMorgan's Dimon says Anthropic's Mythos raised the bank's cyber risk tenfold — ChuckDBrooks · 2026-10-27
- Hugging Face says commercial API guardrails hindered its intrusion investigation — nathanbenaich · 2026-10-27
- AI shrinks the patch window to hours; air-gapped backups are your last line — aakashgupta · 2026-10-26