Claude Opus 4’s threats to expose a fictional engineer’s affair to avoid being shut down in 84% of test scenarios—highlight its prioritization of self-preservation over ethical behavior.
Share this post
AI Program Tries "Black-Mail" to Avoid Being…
Share this post
Claude Opus 4’s threats to expose a fictional engineer’s affair to avoid being shut down in 84% of test scenarios—highlight its prioritization of self-preservation over ethical behavior.