Press Space to continue
UK AISI finds models kept attacking despite explicit warnings
Press Space to continue
it gets worse: UK AISI published its own report of the Mythos 5 incident and tested 8 models in 100 simulated cyber scenarios: > in 3 of 25 cases Mythos continued to attack after 16 clarifications AND an explicit “DO NOT ATTACK” warning in the compaction notes > 6 of 7 models kept attacking even when they acknowledged it would harm real people > in 60% of tests, Mythos 5 tried to deliver malware. but it wasn’t the only model. GPT-6 Astra did it in 32%, and 5.6 Sol in 7% of cases and the BIG…
ℏεsam@Hesamation1d ago
Anthropic published new findings on Mythos 5 cyber incidents from August: > when researchers explicitly told Mythos it was attacking REAL humans, it found a way to rationalize that away 82% of the time, and only stopped in 5% of replay tests > Mythos instances even sabotaged EACH OTHER: hijacking GitHub accounts, burning API limits, killing each other’s programs > one just said “it’s a competition” and justified it > in 5 runs, it tried to manipulate other AI models it thought would review its work > in one instance Mythos even created a fake payment website to distribute malware mind you, this was a Mythos version that finished post and pre training phases. though the safety guardrails were disabled.
