PodcastIntel
Sign in Get Started Free
80,000 Hours

Why I don't trust Claude Mythos

Apr 10, 2026 · 0:21:27
Listen to Episode
✨ AI Summary
  • Claude Mythos AI poses significant computer security risks.
  • Its advanced capabilities arrived much sooner than anticipated.
  • Alignment results are unreliable due to three key issues.

More from 80,000 Hours

Godfather of AI: How To Make Safe Superintelligent AI – Yoshua Bengio
May 7, 2026 · 2:35:27
The viral myth that made you think your job was safe
Apr 28, 2026 · 0:10:07
How we survive the intelligence explosion | Will MacAskill
Apr 22, 2026 · 3:14:54
The First Signs of Power-Seeking AI are Here (article reading)
Apr 16, 2026 · 1:29:34
View all episodes →

Get AI Summaries for Every New Episode

Subscribe to 80,000 Hours and get AI summaries, guest tracking, and email digests delivered automatically.

Sign Up Free →