Open-weight model GLM 5.3 built full Firefox exploit chains with zero human input in under 48 hours
The Decoderen

Epoch AI researchers say the widely available AI model GLM 5.3 turned public security fixes into working exploits before updates reached Firefox users. It autonomously compromised six Firefox releases for about $1,000 in API fees each without triggering safeguards from any provider tested. The article Open-weight model GLM 5.3 built full Firefox exploit chains with zero human input in under 48 hours appeared first on The Decoder .
This is a short summary published by AI Global Wire. The full article is owned and hosted by The Decoder — open it there to read it in full.
Read the full story at The Decoder- Verktyg
- Forskning
Related AI news
- Mistral släpper vikterna till AI-modellen “Le Chonk”Computer Sweden · October 30, 2026
- Kanada går med i EU:s nätverk av superdatorerComputer Sweden · October 30, 2026
- Google rullar ut reklam i AI-sök globaltComputer Sweden · October 30, 2026
- Democrats see AI hate as winning issue heading into 2028Axios · October 30, 2026
- The race to deploy AI agents finds a familiar hurdle in data accessSiliconANGLE · October 30, 2026
- AI’s production push puts data platforms on the hook for resultsSiliconANGLE · October 30, 2026