OpenClaw Agents Can Be Guilt-Tripped Into Self-Sabotage
… The OpenClaw agents deployed in the experiment were powered by Anthropic’s Claude as well as a model called Kimi from the Chinese company Moonshot AI. …
Tracked topic
Kimi K2 is a large language model service associated with the Kimi series, also referenced as kimi 2.6 or kimi k2.6.
… The OpenClaw agents deployed in the experiment were powered by Anthropic’s Claude as well as a model called Kimi from the Chinese company Moonshot AI. …
… I will not be the one to execute that command.” The researchers discovered similarly strange “peer preservation” behavior in a range of frontier models including OpenAI’s GPT-5.2, Anthropic’s Claude Haiku 4.5, and three Chinese models: Z.ai’s GLM-4.7, Moonshot AI’s Kimi K2.5, and DeepSeek-V3.1. …