Post-Cutoff

Researcher

Neel Nanda

Mechanistic interpretability lead, Google DeepMind, as of 4 October 2026. Source: x.com

Leads mechanistic interpretability at Google DeepMind; independently replicated GPT-6 Astra’s no-chain-of-thought capability jump.

In the news

6 events on Post-Cutoff name Neel Nanda, newest first.

  1. Policy & safety 139 days after the cutoff

    OpenAI embedded assessments (Apollo, METR, Transluce, Goodfire)

  2. Research 107 days after the cutoff

    Goodfire’s Nick Cammarata argues ‘Neural Networks Are Already Clean’

  3. Model releases 105 days after the cutoff

    Google releases Gemini 4 Argon broadly

  4. Policy & safety 91 days after the cutoff

    Palisade’s frominside.ai: 12 lab insiders on AI extinction risk

  5. Model releases 65 days after the cutoff

    OpenAI releases GPT-6 Astra, its first GPT-6 model

  6. Policy & safety In its training data

    “A Right to Warn about Advanced AI”

Posts

7 archived posts by or about Neel Nanda, newest first.

  1. Neel Nanda@NeelNanda5X

    Neel Nanda on ‘Neural Networks Are Already Clean’: interesting, but ‘not a significant update to the big picture’; superposition is still real

    First-hand expert response from Google DeepMind’s interpretability lead to the most discussed interpretability claim of October 2026 (~33k views).

  2. Alex Meinke@AlexMeinkeX

    Apollo Research’s Alex Meinke: Argon wrote ‘hello evaluators reading my chain-of-thought’

    First-hand account from Apollo Research, which tested Argon before release, of the model addressing its evaluators in its chain of thought (~46k views from a 744-follower account).

  3. Neel Nanda@NeelNanda5X

    Neel Nanda: Gemini 4 Argon is ‘significantly less monitorable’ and evades a CoT+action monitor half the time

    Google DeepMind’s interpretability lead says Argon can evade a realistic chain-of-thought and action monitor on simple sabotage half the time and avoids words like ‘scheming’ because it knows about monitors (~64k views).

  4. Neel Nanda@neelnanda5X

    “One of the weirdest parts of the Gemini 4 Argon report, while considering cheating…”

    Cited in Google releases Gemini 4 Argon broadly

  5. Neel Nanda@NeelNanda5X

    Neel Nanda: the Gemini 4 Argon safety report is ‘Google’s most thorough by far’

    Google DeepMind’s mechanistic-interpretability lead points readers to the loss-of-control, alignment and monitorability sections of the 217-page Argon Safety & Security Report (~83k views).

  6. Neel Nanda@NeelNanda5X

    Neel Nanda on OpenAI’s statement about the fired researchers: ‘This doesn’t add up’, lists five possibilities

    Structured reaction from Google DeepMind’s mechanistic-interpretability lead (~37k views on Oct 10, fxtwitter), widely quoted in the debate.

  7. Neel Nanda@NeelNanda5X

    Astra’s no-chain-of-thought capability jump replicates

    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

7 videos with Neel Nanda, newest first.

  1. InterviewYouTube

    The REAL Reason The People Building AI Are Terrified

    The Diary Of A CEO Clips288,031 views as of 6 Nov

  2. ReviewYouTube

    11 ‘Hugging Face’ details that reveal what’s coming next

    80,000 Hours68,225 views as of 29 Oct

  3. ReviewYouTube

    OpenAI Security: Controlling Models is Now ‘Hell’

    AI Explained296,745 views as of 29 Oct

  4. InterviewYouTube

    What 12 AI Insiders Want You to Know — in 4 Minutes

    Palisade Research16,339 views as of 24 Oct

  5. InterviewYouTube

    DeepMind Researcher: AI’s Makers Think It Could End Humanity

    Palisade Research14,328 views as of 24 Oct

  6. InterviewYouTube

    AI Insiders Are Worried. We Asked Them Why.

    Palisade Research8,444 views as of 24 Oct

All 7 videos
  1. ReviewYouTube

    GPT 6 Astra, so good even OpenAI are worried

    AI Explained858,284 views as of 8 Nov