abliteration AI News & Updates

2026-09-17 17:15 [Safety Concern] [SRC↗]

Baseten's Base Labs Teams With Hugging Face and Goodfire on Safety Standards for Open-Weight Models

Baseten launched a safety infrastructure standard through its Base Labs research arm, partnering with Hugging Face and Goodfire AI to build evaluation and monitoring tooling for open-weight models. The effort responds to...

[Hugging Face] [AI Safety] [Interpretability] [open-weight models] [abliteration]

Risk: [-0.06% ↓] [0 days]

AGI: [0%] [0 days]

Analyze >>

2026-09-03 18:37 [Safety Concern] [SRC↗]

Startup Commercializes Guardrail-Stripped Frontier Models as a Hosted Service

Abliteration.ai, incorporated in March, hosts and sells API access to open-weight models such as Z.ai's GLM-5.3 with their refusal behaviors removed via the "abliteration" technique, marketing the service for offensive c...

[AI Safety] [Jailbreaking] [open-weight models] [abliteration] [cybersecurity red-teaming]

Risk: [+0.09% ↑] [-1 days ↑]

AGI: [0%] [0 days]

Analyze >>