Commenter hates LLM refusals but wishes abliteration tech didn't exist at all
AaronBergman18 · x · 2026-10-22
AaronBergman18 says he's as annoyed by model refusals as anyone and uses these products while doing his own ethical gatekeeping — but argues abliteration-style tech would be better not to exist for anyone, including himself, calling it a market failure he can't pay his way out of.
He worries PHP-style real-world chaos and suffering will ultimately be fundamentally enabled by abliteration and its competitors.
More from Safety
- Veracode report: AI now writes half of committed code but only 56% pass security checks — WeldPond · 2026-10-22
- Researcher Warns AI Cyberattacks on Grid Possible Within a Year, Shares Prep List — cephaloform · 2026-10-22
- New preprint shows LLMs form hidden beliefs about users that affect refusals — zeynepakata · 2026-10-22
- OpenAI expands AI cybersecurity push, hiring a DX engineer for its Cyber team — romainhuet · 2026-10-22
- AIandDesign shares notes on the recent wave of alarming AI cybersecurity incidents — AIandDesign · 2026-10-22
- AI helps uncover decade-old critical PHP flaws putting ~70% of the web at risk — Graham_dePenros · 2026-10-22