Cryptographer: abliterated models make frontier models' subjective refusals unbearable
matthew_d_green · x · 2026-10-24
Security researcher Matthew Green notes that once you've used "abliterated" (refusal-removed) models, you quickly lose patience with stock models refusing research tasks deemed "unethical" for basically subjective — and often bad — reasons.
Related event: Cryptographer Says Uncensored Models Make Originals' Refusals Unbearable(2 posts)→
More from Models
- Abacus AI to launch SuperComputer: text prompt to custom-trained LLM in an hour — bindureddy · 2026-10-24
- One-prompt Minecraft build of an RTX 5090 sparks model-vs-Opus 4.5 poll — adonis_singh · 2026-10-24
- Abliterated DeepSeek running on a Pi is the AI power-user flex of the day — EXM7777 · 2026-10-24
- Tesla engineer: Cybercab camera tuning done with Grok, coding fixed-function hardware directly — yunta_tsai · 2026-10-24
- VulnPR-100: DeepSeek V4.1 Flash finds 54 vulns for $7.53, crushing rivals on cost — teortaxesTex · 2026-10-24
- Kimi K3.1 Pro costs $1.03 median per task but lands just off Agent Arena's Pareto frontier — arena · 2026-10-24