Jan Leike

@janleike

AI research @AnthropicAI. Previously OpenAI & DeepMind. Optimizing for a post-AGI future where humanity flourishes. Opinions aren't my employer's.

Vibe and topics

Based on 200 recent X posts · click a vibe for evidence

Vibe

Informing

Informing30.9%

Teaching17%

Announcing15.6%

Hopeful13.7%

Supportive11.5%

Provocative7.2%

Humorous2%

Other2.2%

Topics

Scalable Oversight

Scalable Oversight19.9%

AI Safety Audits17.4%

Jailbreak Robustness16.6%

Automated Alignment Research12.4%

AI Regulation11.5%

Model Interpretability9.4%

Claude Alignment6.9%

Weak-to-Strong Generalization6.1%