Rohin Shah

97Following219Top Followers11.4KTotal Followers

BIO

AGI Safety & Alignment @ Google DeepMind

#772inTech

Vibe and topics

Based on 180 recent X posts · click a vibe for evidence

Vibe

Informing

Informing42.5%

Announcing36.4%

Teaching10%

Hopeful5.6%

Supportive3.6%

Other1.9%

Topics

Alignment Newsletter

Alignment Newsletter55.7%

Deceptive Alignment8.6%

Frontier Safety Framework7.4%

Goal Misgeneralization7.1%

Minecraft Benchmarks6.3%

Chain-of-Thought Monitoring5.6%

Mechanistic Interpretability4.8%

AI Safety Hiring4.6%

Pieter Abbeel

@pabbeel

Berkeley & Amazon

Sam Bowman

@sleepinyourhat

AI alignment + LLMs at Anthropic. On leave from NYU. Views not employers'. No relation to @s8mb. Into @givingwhatwecan.