2d • News
Anthropic's AI wrote a Chrome exploit for $2,283 💀
Researchers found that Claude Opus — a model anyone can access right now — successfully wrote a working Chrome browser exploit. Cost: $2,283 in API calls. This comes as Anthropic separately withheld its Mythos security model from public release, citing danger. But if the publicly available version is already doing this, the line between "safe" and "dangerous" AI is a lot blurrier than we're being told.
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
0
0 comments
Anthropic's AI wrote a Chrome exploit for $2,283 💀
skool.com/ai-agents-openclaw
OpenClaw builders sharing real agent setups, cost optimization, configs, and advanced workflows. Build smarter AI with hands on support.
Leaderboard (30-day)
1
+17
2
+10
3
+6
4
+6
5
+5
Powered by