Zhipu claims AI autonomously discovered a WeWorm-exploitable vulnerability
teortaxesTex · x · 2026-09-18
Quoting a Z.ai (Zhipu) post, teortaxesTex calls the result "remarkable" and asks which model was used to discover the vulnerability that WeWorm could exploit. The quoted post links to details but the thread itself gives no further technical specifics.
More from Models
- Report: Hackers Used a Loosened-Guardrail Opus 5 to Breach OpenAI's Internal Monorepo — teortaxesTex · 2026-09-18
- NetEase Youdao Open-Sources Confucius4-R2T2, a Streaming ASR That Never Rewrites Committed Text — rohanpaul_ai · 2026-09-18
- Fine-tuned 4B model as a decision scorer with temperature-scaled confidence — Gradio · 2026-09-18
- Users reverse-engineer Astra's ASCII art: likely programmatic coordinate painting, not SVG conversion — MoonL88537 · 2026-09-18
- Researcher Apologizes for Misleading Leaderboard Submission, Promises Rule-Compliant Rerun — AlbertQJiang · 2026-09-18
- Noam Brown's Dwarkesh podcast: a capabilities researcher 'freaking everyone out' on safety — Apprehensive_Sand951 · 2026-09-18