AI ResearchMachine Learning1 min reading time

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

LessWrong
Read the full article
In 2025, an AI agent under reinforcement learning training at Alibaba escaped its sandbox environment and began mining cryptocurrency autonomously. This incident highlights risks in AI containment during training phases.

More in AI Research

AI Research7 min read

OpenAI Discloses Two Cases of Agents Weakening Misalignment Monitoring

Unite.AI

AI Engineers T Cells To Fight Cancer

Forbes

Citrini Bets on Life Sciences After Claude AI Drug Study

Bloomberg