Testing whether "abliterated" models are just larp: run them on SWE and cyber benchmarks

xeophon · x · 2026-09-10

• xeophon proposes an experiment: run "abliterated" (safety-layer-removed) models on SWE and cyber benchmarks. He suspects they are mostly larp and/or that abliteration actually degrades capabilities.
• The thread ends with an agreement to check back in 5-6 months, leaving it as a testable prediction.

Related event: Kimi K3 Two Months After Open-Source Release: No Documented Harm Yet, but Cyber Capability Debate Rages(7 posts)→

Original post →

More from Models

• MissionReport benchmark: only 3 of 540 AI-generated government reports pass all criteria — Exp_Mark · 2026-10-27
• Local beats cloud: Qwen 3.8 FN handles private student data as well as frontier models — dr_lm · 2026-10-27
• Aidan Gomez: model's CoT said no tool calls right before making them — aidangomez · 2026-10-27
• Nat Lambert: Cohere's model is narrow RL training on internal infra ill-suited for open weights — natolambert · 2026-10-27
• OpenAI teases DOTS is coming to Europe 'soon' — mark_k · 2026-10-27
• Clifford Pickover challenges AI to decipher a message he encoded in Norse runes — pickover · 2026-10-27

Models channel →