AISimon Willison2h ago
Cybersecurity Looks Like Proof of Work Now
TL;DRUK researchers tested Claude AI's cybersecurity abilities and confirmed it's unusually effective at hacking tasks.
Why it matters: Powerful AI systems can now perform sophisticated cyberattacks, raising urgent questions about AI safety and dual-use risks.
Cybersecurity Looks Like Proof of Work Now The UK's AI Safety Institute recently published Our evaluation of Claude Mythos Preview’s cyber capabilities, their own independent analysis of Claude Mythos which backs up Anthropic's claims that it is exceptionally effective at…
Read full articleSource: Simon Willison · Opens in new tab