I call bullshit on all of this "going rogue", it wouldn't only do this if it was explicitly told to, or the training / re-enforcement data deliberately planted instructions
https://the-decoder.com/anthropic-says-its-unreleased-model-is-both-more-capable-and-better-aligned-than-mythos-5-1/
https://the-decoder.com/anthropic-says-its-unreleased-model-is-both-more-capable-and-better-aligned-than-mythos-5-1/
5β€οΈ5π―1π1