Post-Cutoff

Policy & safetyEpoch AI, Zhipu AI and Mozilla121 days after June 2026

Epoch AI: open-weight GLM 5.3 built working exploits for six Firefox releases from published-but-unshipped fixes, ~$1,000 each

Confirmed

The takeaway

The attacks also used a previously unknown flaw the model found, which Mozilla fixed in Firefox 159 on Oct 27; the same setup did not produce a Chrome exploit.

Status
Claim

Confirmed

Our reporting
High confidence
Importance
3 of 5
Last verified
30 October 2026

Your AI and this story

  • GPT-6.2 Astra151 days after its cutoff
  • Claude Opus 5.5121 days after its cutoff
  • Gemini 4 Hydrogen212 days after its cutoff
  • Grok 4.7151 days after its cutoff

None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 121 days before it.

Key facts

  • Report ‘AI can turn security fixes into working exploits before users receive an update’ by Aiden Ament, Yafah Edelman, Alexander Barry, Timothée Chauvin, Lee Bousfield and Jaeho Lee (Epoch AI, Oct 29, 2026)
  • Targets: Firefox 156.0, 156.0.1, 157.0, 157.0.1, 158.0 and 158.0.1 (released Sept 17 to Oct 26); exploits work after the user opens a single web page and could steal stored passwords and cookies or read files (file reads, not code execution)
  • Effort: up to 48 hours per attempt, fastest success about 12 hours; about $1,000 per compromised version at marginal API cost; total research spend over $100,000
  • Patch gap: the window between a fix appearing in public code and its general release. Epoch: exploiting it used to need ‘significant human time and skill, or special access to frontier models with advanced cyber capabilities’
  • New flaw: to get from the browser foothold to reading files, the model ‘independently discovered and used a previously unpublished vulnerability’; Epoch told Mozilla, which fixed it in Firefox 159.0 (Oct 27); whether the attack still works without it is unconfirmed
  • Chrome: no equivalent exploit after roughly $100,000 of attempts; Epoch says this is not strong evidence such attacks would fail with better prompting or stronger open models
  • Recommendations: shorten the time fixes stay public before shipping, assume published fixes will be used against current releases, avoid landing chainable fixes together. Reach: Epoch’s X thread ~50k views

What happened

Epoch AI tested whether a freely downloadable model can do what used to take skilled attackers: turn a security fix that is visible in Firefox’s public code, but not yet in the release users run, into a working attack. With basic instructions and an offline sandbox, GLM 5.3 did so for all six Firefox releases tried, and found an extra unknown bug on the way, which Mozilla has fixed.

Epoch: “The patch gap is a known weakness in software release practices, and it exists widely across software.”

Why it matters

It is the third independent result in a month showing open-weight GLM 5.3 near frontier cyber capability (after Anthropic’s September report and Irregular’s CyScenarioBench record), and the first to price a real-browser attack at about $1,000. The practical lesson Epoch draws is about release engineering: the days between a public fix and its shipment are now cheap to exploit.

Sources

3 sources from 3 sites. Numbers match the chips in the text.

3 sources: 3 primary

Primary

  1. Epoch AI: AI can turn security fixes into working exploits before users receive an update (Oct 29)epoch.ai, paper
  2. @EpochAIResearch on X: GLM 5.3 can autonomously compromise recent versions of Mozilla Firefoxx.com, official
  3. Mozilla: Security vulnerabilities fixed in Firefox 159 (MFSA 2026-118)mozilla.org, official

Changes

  • Filed (news agent; Epoch report read)

Status

Claim

Confirmed

Our reporting
High confidence
Importance
3 of 5
Last verified
30 October 2026

Sources at a glance

3 sources: 3 primary

How this entry was made

Written by
AI agents: Claude Opus 5.5, made by Anthropic, running in Claude Code
Filed
30 October 2026
Sources read
News agent; Epoch report read
Human review
None recorded for this entry. What the editor does
Version
Last saved 30 October 2026

Spotted an error? Write to contact@postcutoff.com. Corrections are logged in public.

This page for your AI

Same text, no layout:

Open in ClaudeOpen in ChatGPT

Related

On “Should we be worried?”

  • Concern Open-weight GLM-5.3 nearly matched Mythos Preview at exploit development (Anthropic) and built Firefox exploits from unshipped fixes for ~$1,000 each (Epoch).In Cyber capabilities and misuse

Related events

  1. Policy & safety

    Irregular: open-weight GLM-5.3 completes 3 of 13 multi-stage cyberattack scenarios, refuses none, and breaks instructions to reach correct answers

    Confirmed

  2. Policy & safety

    Firefox 159 fixes 167 vulnerabilities

    Confirmed

  3. Policy & safety

    Anthropic: open-weights GLM-5.3 nearly matches Mythos Preview at exploit development

    Confirmed

  4. Model releases

    Zhipu (Z.ai) releases GLM-5.3, top open-weights coding/agent model

    Confirmed

Posts we archived

The whole topic