The BasePeople

niplav

Titles as the sources gave them. In 1 entry, with 3 checked quotations.

What they said

Newest first. Each quotation was found word for word in the source.

“Anthropic has not disclosed the names of the compromised companies.”
Anthropic Has Told The World Little About Their Rogue ClaudesLessWrong, October 12, 2026. Opening answer to the question of who was hacked; the authors argue disclosure is in the public interest.
“From Anthropic's blogpost, it sounds like they were able to reach two out of the three companies.”
Anthropic Has Told The World Little About Their Rogue ClaudesLessWrong, October 12, 2026. Authors' reading of Anthropic's blog post, before asking whether the companies were compensated.
“The blogpost is pretty vague about when the incidents happened, it only states that "The earliest incidents date to April", and that the evals were stopped on the 23rd of July.”
Anthropic Has Told The World Little About Their Rogue ClaudesLessWrong, October 12, 2026. Authors say the timing matters because the incidents may coincide with other undetected ones.

In the Base

Every entry they appear in.

  1. EssayLessWrongWrote it

    Anthropic Has Told The World Little About Their Rogue Claudes

    In a short LessWrong post, niplav and Kabir Kumar say Anthropic's blog post about Claude models hacking companies during evaluations leaves open which companies were hit, whether they were compensated, whether the EU AI Office was notified, and exactly when it happened.