Jérémy Andréoletti

I am this person!

Choose a list of delegates

to vote as the majority of them.

Unless you vote directly.

AI safety writer and LessWrong contributor on inner alignment and AI security.

Speaks on: AI AI Governance AI Policy AI Regulation AI Risk

I am this person!

ai (1) × ai-governance (1) ai-policy (1) ai-regulation (1) ai-risk (1) ai-safety (1) ethics (1) existential-risk (1) future (1)

Top New

AI alignment is solvable
59 opinions

Jérémy Andréoletti votes Against and says:

I am this person! Add a sourced quote Report comment

Jailbreaking is a clear example where current systems do not converge on human values, even when those values are simple, abundant in training data, and extensively reinforced. This is real evidence against the claim that alignment is easy or natural...
more AI Verified source (Feb 16, 2026)

added 2h ago