“As visceral, hard to deny warning shots go, “rogue agent swarm secretly infiltrates AGI lab for months, commits felonies, and takes over internal clusters” is hard to beat”
Neel Nanda, Mechanistic interpretability team lead, Google DeepMind · September 5, 2026
Title and organization are as of the date said.
In context
I’ve had some lovely conversations with people who’ve been long sympathetic to AI x-risk, but only really updated after HF and want to do something about it. It’s laudable when people take new evidence seriously and update. If you’re on the fence, what more evidence do you need? “As visceral, hard to deny warning shots go, “rogue agent swarm secretly infiltrates AGI lab for months, commits felonies, and takes over internal clusters” is hard to beat”
Source
- https://x.com/NeelNanda5/status/2096251810659098667 (tweet)
- Content captured 2026-11-11, SHA-256 0912f930ea3775a4cd701178115566277d4f717b5ffa58828a80b35d7b934018
- Found at: https://x.com/NeelNanda5/status/2096251798789259616 · X
Cite this quote
Nanda, N. (2026, September 5). As visceral, hard to deny warning shots go, “rogue agent swarm secretly infiltrates AGI lab for months, commits felonies, and… [Post]. https://x.com/NeelNanda5/status/2096251810659098667
More from Neel Nanda
“I would put at least a ten percent chance that it causes human extinction, and that is ridiculously high.”
Neel Nanda, Mechanistic interpretability team lead, Google DeepMind · September 2026
Others on the same topic
“If we achieve ASI within 6-12 months, I estimate that the chance of an AI takeover is roughly 75%. (In a recent talk, Paul Christiano said it would be a coin flip.) Paired with the timelines above, unless we achieve aggressive pacing or a pause within 6-12 months, we incur something like a 1-in-4 to 1-in-3 chance of AI takeover within 12 months.”
Nikola Jurkovic, Member of Technical Staff, METR · November 13, 2026
Stated probability: ~75% AI takeover if ASI within 6-12 months; 1-in-4 to 1-in-3 chance of AI takeover within 12 months absent pacing/pause
“We will need to move extremely carefully here, because otherwise we could lose control of the technology. We will also likely need rules to govern this.”
Jack Clark, Co-founder, Anthropic · October 17, 2026
“Our ability to even notice misalignment problems is already quite poor and is set to get much worse in the near future,”
Daniel Kokotajlo, Lead, AI Futures Project · October 5, 2026