Rohin Shah 🇺🇸
Rohin Shah leads AGI Safety and Alignment at Google DeepMind and publishes research and first-person analysis on alignment, AI control, oversight, and frontier-model governance.
- Evidence items
- 3
- Toward pressure
- +0.02
- Away pressure
- −0.09
- Net attributed pressure
- -0.07
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Current and former organisations
These dated, source-backed roles support navigation between people and companies. They do not attribute a story or change the Doom Index.
First-person and official sources
These sources guide discovery. A statement still needs a dated, attributable, source-backed evidence assessment before it can affect the index.
- interview feed80,000 Hours interviews with Rohin Shah
- personal siteRohin Shah
Assessments involving Rohin Shah
Rohin Shah argues short-horizon training weakens default takeover claims
Rohin Shah argues that reinforcement learning over week- or month-scale trajectories more naturally produces short-horizon reward hacking than ambitious world-takeover goals. He treats catastrophic misalignment as plausible but not the default, while warning that current alignment results do not resolve future superhuman-oversight failures.
Rohin Shah warns a short AI pause could reduce safety time
Rohin Shah supports enforceable global slowing, but identifies a countervailing mechanism: hardware, algorithms, and investment could keep advancing during a training pause while safety researchers lose access to intermediate models. A poorly designed pause could therefore reduce capabilities-adjusted safety time without proportionally delaying dangerous systems.
Rohin Shah argues advanced AI need not be goal-directed
Shah argues that superintelligent systems need not be goal-directed and proposes norm-following, corrigible, bounded, and episodic services as safer architectures. He also warns that imperfect imitation learning could still create dangerous consequentialist planning.