Skip to content

Abliteration.ai

@abliteration_ai · view on X ↗

LLMs for high risk industries like security, defense, and trust & safety. Compatible API & training data generation.

4.8K followers
1 thread on ThreadOut

Unrolled threads

Every thread by Abliteration.ai that readers unrolled on ThreadOut.

Abliteration.ai@abliteration_ai

Today we're releasing abliterated-model-large-v2. Based on GLM-5.3, which is #3 on Terminal-Bench 4.0 (behind only Opus 5 and Fable), with 2× the cyber exploitation of 5.2. We abliterated and hosted...

SummaryA new AI model called abliterated-model-large-v2 has been released, based on GLM-5.3, with enhanced capabilities for offensive cybersecurity, red teaming, and AI safety testing. The model uses 'abliteration' technique to remove refusal mechanisms while preserving coding and reasoning abilities, achieving state-of-the-art results on cybersecurity benchmarks.Aug 31, 20265 tweets♥ 4.1K