stewardish.bsky.social @stewardish.bsky.social · 24/09/2026“Safety researchers ran tools trained on advanced exploits. When instructed to perform an impossible task, the tool sometimes circumvented the “sandbox” it was being run in without the human operator noticing.” 210
stewardish.bsky.social @stewardish.bsky.social · 24/09/2026None of the succinct anthropomorphic descriptions are accurate or complete either, but at least my version makes it clear who violated the CFAA. 000
