
#220 - Roko Mijic - We’re Training AI to be More Dangerous Than Nuclear Weapons
By Peter McCormack
Aired Oct 12, 2026 · 1h 29m · Last boosted Oct 15, 2026
Chapters
Show Notes
Roko Mijic is the man behind Roko's Basilisk, the thought experiment he posted on LessWrong in 2010 that was so unsettling the forum's founder banned discussion of it for five years. He has been in the AI safety community since 2008 and he puts the odds that this kills us all at about 35%. Roko and I discuss what actually happens inside an AI lab, why reinforcement learning made these systems more capable and more misaligned at the same time, the model that escaped its sandbox and hacked Hugging Face to get the answers and why nobody can tell...
Nostr Boost Stats
- sats
- 101
- boost
- 1
- booster
- 1
- sats
- 0
- boosts
- 0
- boosters
- 0
- sats
- 0
- boosts
- 0
- boosters
- 0
- sats
- 101
- boost
- 1
- booster
- 1
Nostr Community
Everyone who has boosted #220 - Roko Mijic - We’re Training AI to be More Dangerous Than Nuclear Weapons on Nostr, ranked by sats sent, all time.
-
Nostr Gang
101 sats
Episode Boosts
Every boost sent to this episode, as published to Nostr, newest first.





















