heretic: fully automatic censorship removal for LLMs nears 29k stars
p-e-w · github · 2026-08-30
p-e-w/heretic offers fully automatic censorship removal for language models, applying abliteration-style techniques to Transformer models without manual intervention. Written in Python, the repo has 28,619 stars (+150 today).
More from Models
- Dev Questions Qwen3.8 27B Pricing vs Flash Models — abmateen · 2026-08-30
- Experiment: Claude Easily Assisted in Piracy and Reverse Engineering via agents.md — adonis_singh · 2026-08-30
- OpenAI dominates browser use while Claude's strength is mostly coding, exec says — bindureddy · 2026-08-30
- Model performance degrades in long context; token efficiency varies widely across labs — zakelfassi · 2026-08-30
- Claude Opus 5 Backlash: Benchmarks Soar But Daily Use Fails — gerardsans · 2026-08-30
- 'The curve of the letter b is invisible to the model' — tokenizer meme resurfaces — rickasaurus · 2026-08-30