Heretic 2.0 Released as General-Purpose Model Modification Tool

Heretic 2.0 launches, expanding from a censorship-removal tool into general-purpose model modification that can suppress slop, reduce sycophancy and alter emotional alignment. The project reports 37k GitHub stars, over 8,500 Hugging Face models and 88 million downloads. It replaces directional abliteration with the new Arbitrary-Rank Ablation, moves to a plugin architecture, and is not backward compatible.

• Hugging Face Releases MoE Training Handbook Built on Megatron-LM2026-11-05
• Hugging Face hosts quantization workshop livestream2026-11-05
• OpenAI launches GPT-6 Cyber cybersecurity model2026-11-05
• CCORE Releases GLB-3D-Coder 4B With Full Weights2026-11-05
• Phonon TTS brings high-quality on-device speech, tops benchmarks2026-11-05