Matthew Green clashes with MalwareTech over abliterated GLM exploit claims
MalwareTechBlog · x · 2026-11-09
Security researcher MalwareTech and cryptographer Matthew Green are publicly arguing over "abliterated" GLM. Green says MalwareTech has confidently told hundreds of thousands of followers that no non-expert could build a useful exploit with it — without ever touching the model directly. MalwareTech counters that he works with models extensively but prefers his automation pipeline, and that abliterated GLM is just a worse regular GLM: abliteration degrades more than refusals, so it's only worth using if the stock model keeps refusing.
More from Fun
- Anthropic RL environment engineer meme sparks a question about intelligence — fkasummer · 2026-11-09
- Anthropic bets on healthcare and biology as Claude sole-authored paper fuels hidden-model speculation — coherence · 2026-11-09
- The 'Zuckerberg has no scandals and carves Roman statues' meme goes viral — Kyrannio · 2026-11-09
- Switch 2 emulator Lichii hits stable 60fps Zelda, adds experimental DLSS support — CtrlAltDwayne · 2026-11-09
- Finding the direction of steepest descent: scenic Marin roadside photo as gradient descent pun — dumierhan · 2026-11-09
- Investors split as Jensen Huang scandal rattles AI trade: "impossible this isn't the bottom" — econoar · 2026-11-09