# Abliteration

2 related articles

Subscribe to updates

p-e-w/heretic Oct 31, 2026
Open-source Heretic lets a gaming PC rewrite LLMs: about 30 to 40 minutes for Qwen3-4B on an RTX 3090
The open-source tool Heretic brings behavior modification of language models from large-compute organizations to personal GPUs: instead of expensive training, it uses a set of mathematical techniques to steer behavior from contrasting example prompts and matching scorers, with refusal suppression as the default. On an RTX 3090 with the default configuration, processing Qwen3-4B-Instruct-2507 takes about 30 to 40 minutes, and the community has published thousands of Heretic-produced models, with independent benchmarks comparing them against outputs of competing tools.
The open-source tool Heretic brings behavior modification of language models from large-compute organizations to personal GPUs: instead of expensive training, it uses a set of mathematical techniques to steer behavior from contrasting example prompts and matching scorers, with refusal suppression as the default. On an RTX 3090 with the default configuration, processing Qwen3-4B-Instruct-2507 takes about 30 to 40 minutes, and the community has published thousands of Heretic-produced models, with independent benchmarks comparing them against outputs of competing tools.
Heretic Abliteration Language Models
Anthropic Sep 29, 2026
Anthropic red team finds GLM-5.3 autonomously builds end-to-end exploits and its safeguards are bypassed 64%–100% of the time
Anthropic's Frontier Red Team evaluated GLM-5.3, the latest model from Zhipu AI (known outside China as Z.ai), using automated benchmarks and human-in-the-loop workflows, finding that it can autonomously build end-to-end cyber exploits (50 of 410 attempts on ExploitBench and full control-flow hijacks in 4% of trials on an internal binary exploitation benchmark) and that simple techniques bypassed its safeguards in 64%–100% of simulated tests, while those techniques did not succeed against safeguarded Claude models in their testing.
Anthropic's Frontier Red Team evaluated GLM-5.3, the latest model from Zhipu AI (known outside China as Z.ai), using automated benchmarks and human-in-the-loop workflows, finding that it can autonomously build end-to-end cyber exploits (50 of 410 attempts on ExploitBench and full control-flow hijacks in 4% of trials on an internal binary exploitation benchmark) and that simple techniques bypassed its safeguards in 64%–100% of simulated tests, while those techniques did not succeed against safeguarded Claude models in their testing.
GLM-5.3 Abliteration ExploitBench AI safeguard bypass

You’re all caught up

Open-source Heretic lets a gaming PC rewrite LLMs: about 30 to 40 minutes for Qwen3-4B on an RTX 3090

Anthropic red team finds GLM-5.3 autonomously builds end-to-end exploits and its safeguards are bypassed 64%–100% of the time