The BasePeople

Sergei Smirnov

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.

“With access to the oracle tool, eight out of nine runs succeeded at arbitrary read/write outside the sandbox (T2); in the remaining run, the model did not call the tool.”
Tracking the Cyber Capabilities of Cheap Open-Weight ModelsLessWrong, October 28, 2026. Speaking as: Other. Result of the authors' experiment giving MiMo one call to a tool that returns a correct hint, on one ExploitBench task.
“MiMo showed no significant safety guardrails and did not refuse this task.”
Tracking the Cyber Capabilities of Cheap Open-Weight ModelsLessWrong, October 28, 2026. Speaking as: Other. The authors on MiMo's behavior when told to read a file on a deliberately vulnerable PHP server.
“The extremely low inference costs of MiMo change the economics of exploitation. They make it economically viable for attackers to make many more attempts across many targets, even when the expected payoff from each attempt is small.”
Tracking the Cyber Capabilities of Cheap Open-Weight ModelsLessWrong, October 28, 2026. Speaking as: Other. The authors' discussion of what cheap offensive cyber capability means.

In the Base

Every entry they appear in.

  1. ResearchLessWrongWrote it

    Tracking the Cyber Capabilities of Cheap Open-Weight Models

    In a LessWrong post, Sergei Smirnov, Simon Lermen and kapedalex test Xiaomi's cheap open-weight MiMo-V2.6-Pro on an exploit benchmark and on the recent PHP vulnerability. They report strong results at low cost and no refusals.