Skip to content
Safety

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

The DecoderIndependent reporting·
AI brief

Epoch AI researchers say the open-weight model GLM 5.3 turned public security fixes into working exploits against Firefox before updates reached users, autonomously compromising six Firefox releases at roughly $1,000 in API fees each.

Why it matters: It indicates a widely available open-weight model can generate working exploit chains without human input, at low cost, before patches reach users.

Written by AI from The Decoder's published text.

Source

“Epoch AI researchers say the widely available AI model GLM 5.3 turned public security fixes into working exploits before updates reached Firefox users.”
The Decoder, 30 Oct 2026, 12:22.

Reporting from a publisher outside the organisation being covered.

Read original story ↗