p-e-w · Alignment & Safety
Heretic
Fully automatic censorship removal for transformer LLMs using directional ablation plus an Optuna optimizer — produces decensored models that match human-expert abliterations with much lower KL divergence.
Open the source ↗Similar Research & Safety releases
- Concerning behaviour from Qwen3.8-Flash-Next
Cohere · Open-weight model safety · Week 45, 2026
- ExploitGym Incident
OpenAI (with Hugging Face) · Red Teaming · Week 30, 2026
- DeepTeam
Confident AI · Red Teaming · Week 45, 2025
- Anthropic files for an IPO (Form S-1)
Anthropic, PBC · IPO Filing · Week 45, 2026
- PhotoGuard
MadryLab (Hadi Salman, Alaa Khaddaj, Guillaume Leclerc, Andrew Ilyas, Aleksander Madry) · Image edit protection · Week 45, 2026
- Claude finds router privacy flaws
codila (@0xCodila) · Router privacy audit · Week 45, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.