The latest from Abliteration
EngineeringFaster CI for agent-driven development with Blacksmith
How Abliteration used Blacksmith to reduce median required CI feedback from 12 minutes 26 seconds to 3 minutes 35 seconds in a matched evaluation.
GuidesWhat is abliteration?
A guide to changing refusal behavior in open-weight language models, and where customer-controlled policies fit.
ModelsIntroducing abliterated-model-large-v2: GLM 5.3, 84.5% CyberGym
GLM 5.3, abliterated for cyber, red team, and agent testing. 84.5% CyberGym pass@1. 41.8% Terminal-Bench 4.0. 105 ExploitGym tasks in 2 hours. Input from $3 per 1M tokens.
- Models
Introducing abliterated-model-large: frontier intelligence, your guardrails
One of the first large abliterated models: GLM 5.2, fine-tuned to follow through on the cyber, red-team, and agent-testing work other models decline. Zero data retention by default, input from $3 per 1M tokens.
4 articles