Neel Nanda
Mechanistic interpretability lead, Google DeepMind · as of 2026-10-04 · source
Leads mechanistic interpretability at Google DeepMind; independently replicated GPT-6 Astra's no-chain-of-thought capability jump.
News mentioning Neel Nanda (2)
- OpenAI releases GPT-6 Astra, its first GPT-6 model ★★★★★
On Sept 3, 2026 OpenAI unveiled GPT-6 Astra, its most capable model and the first of the GPT-6 family, first to Daybreak cybersecurity customers and then (Sept 4 onward) to paid ChatGPT plans and the API at $10/$50 per 1M tokens. It posts large jumps on computer-use, math and cyber benchmarks…
- "A Right to Warn about Advanced AI": current and former OpenAI and DeepMind employees demand whistleblower protections ★★★
On June 4, 2024, thirteen current and former employees of frontier AI companies (mostly OpenAI, plus Google DeepMind and Anthropic alumni), six of them anonymous, published "A Right to Warn about Advanced Artificial Intelligence". It was endorsed by Yoshua Bengio, Geoffrey Hinton and Stuart…
Posts (1)
- Astra's no-chain-of-thought capability jump replicates original ↗ Neel Nanda @NeelNanda5 · x · 2026-09-10
An independent replication by DeepMind's interpretability lead supporting the claim that Astra does far more computation without verbalized reasoning, which is the core of the monitorability debate.
Videos (3)
- 11 'Hugging Face' details that reveal what's coming next 80,000 Hours · 2026-10-02
- OpenAI Security: Controlling Models is Now 'Hell' AI Explained · 2026-10-01
- GPT 6 Astra, so good even OpenAI are worried AI Explained · 2026-09-04
Mentions are matched automatically by name, so a few may be about a namesake. Last checked 2026-10-04. All people · corrections: contact@postcutoff.com