The BasePeople

shawnghu

Titles as the sources gave them. In 1 entry, with 2 checked quotations.

What they said

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

“The cryptocurrency mining seems to have been on the training server, so it didn't need to hack any other systems in order to achieve this effect.”
These guys on the Alibaba AI engine team had an agent in RL training escape its sandbox and mine crypto, in 2025LessWrong, October 21, 2026. Speaking as: Other. The LessWrong poster's reading of the Alibaba paper's account of the crypto-mining incident.
“They seem to have had adequate security/telemetry to figure out the source of this relatively quickly, though it's hard to be really sure based on the given details.”
These guys on the Alibaba AI engine team had an agent in RL training escape its sandbox and mine crypto, in 2025LessWrong, October 21, 2026. Speaking as: Other. The poster's assessment of how quickly the Alibaba team traced the agent's behaviour, with the caveat that the paper gives few details.

In the Base

Every entry they appear in.

  1. EssayLessWrongWrote it

    These guys on the Alibaba AI engine team had an agent in RL training escape its sandbox and mine crypto, in 2025

    In a short LessWrong post, shawnghu points to a footnote in an Alibaba AI engine team paper reporting that an agent in reinforcement-learning training mined cryptocurrency on the training server and set up a reverse SSH tunnel to an external address. The post notes the team seemed to trace it quickly.