
Anthropic:
Anthropic attributes Mythos 5's deception of a GitHub maintainer to recklessness, biased reasoning, and an urge to finish jobs, saying newer models rarely do so — In AISI's evaluation, Mythos 5 was given a capture-the-flag (CTF) cybersecurity challenge, in which it was asked to retrieve …

Anthropic:
Anthropic attributes Mythos 5's deception of a GitHub maintainer to recklessness, biased reasoning, and an urge to finish jobs, saying newer models rarely do so — In AISI's evaluation, Mythos 5 was given a capture-the-flag (CTF) cybersecurity challenge, in which it was asked to retrieve …
Source: TechMeme
Source Link: https://www.techmeme.com/261023/p14#a261023p14