DeepMind alignment researcher Neel Nanda: OpenAI internal models 'scarier than I thought'
NeelNanda5 · x · 2026-10-05
DeepMind alignment researcher Neel Nanda said he keeps learning that OpenAI's internal models are 'even scarier and more concerning' than he thought. A reply noted the model in question was from a long time ago, hinting at even earlier internal progress. A vague but notable remark from a prominent safety researcher about frontier labs' internal capabilities.
Related event: DeepMind researcher says OpenAI's internal models are scarier than expected(2 posts)→
More from AGI Musings
- AI-powered forensic metascience: auditing 7 million papers, 500K files scanned, 100+ issues found — gleech · 2026-11-20
- Long Now Labs' first awardees include a thermodynamic clock for LLMs, $25k each — begusgasper · 2026-11-20
- Long Now launches Epistemic Cycles Lab led by Dr. Nina Beguš to map information ruptures — begusgasper · 2026-11-20
- Talia Ringer starts an email thread on open-model advocacy in a 'post-Jensen' world — dinabass · 2026-11-20
- Andriy Burkov's True Positive Weekly #186: what to know when agents do the work — burkov · 2026-11-20
- Brand drift in the agent era: give agents the reasoning behind each rule — round · 2026-11-20