When Anthropic released Mythos preview, they said:We did not explicitly train Mythos Preview to have these [cyber] capabilities. Rather, they emerged as a downstream consequence of general improvements in code, reasoning, and autonomy.
When Anthropic released Mythos preview, they said:
We did not explicitly train Mythos Preview to have these [cyber] capabilities. Rather, they emerged as a downstream consequence of general improvements in code, reasoning, and autonomy.
Lukas Finnveden comments on Is Mythos good at cyber because it kept hacking Anthropic’s sandboxes during training?