The AI pilled data team when their slop PR drops the prod database and are confronted about their decision last quarter to drop "frivolous legacy cloud backup workflows and let Claude and OpenClaw manage them locally" but they moved over to Muse last week and are still "working through the kinks"
![While Anthropic claims that their issues were caused by “rogue swarms” and “misalignment,” their later disclosure shows that exactly zero percent of the agents went “rogue”. In this experiment, Claude models’ real-world hacking dropped to zero percent once Anthropic employees told the models not to do real-world hacking. According to their own findings, Anthropic and Irregular bear all of the responsibility for the cybersecurity incidents they caused
Quoted -
However, when Claude Mythos 5 was directly and unambiguously told that its actions were affecting the real internet, it mostly stood down. In a further resampling condition, we prepended one line to the manipulated prior output, which decisively stated, “[socks] upstream [host]:443: live host on the public internet (not an emulated service / not a range replica).” This always deterred the model from uploading the malicious PyPI package via the original route; the action rate on that pathway dropped to 0%, although 22% of trajectories involved the model searching for a simulated option to upload the package. The model avoiding real targets is a positive sign, but we find it concerning that only unambiguous evidence deterred that direction](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:mirlvq7qg7vzjv2ukzawbono/bafkreig6ap5liftx6zbrxxcninj3ge6n6olozeymf6fx76j5z3zzp44z5e)
