Tagged with

3 articles found

AI “Torture Chamber” on GitHub Sparks Ethics Meltdown: What the Pain Signal Research Actually Found

A developer built an AI torture chamber after researchers identified a ‘pain’ signal in LLMs. GitHub took it down. Here’s what the science says.

#AI ethics#LLM Safety#Mechanistic Interpretability

abliteration

Abliteration Autopsy: 85 GPU-Hours of Forensics Reveal Which Safety Removal Actually Works

An open-source toolkit compared five abliteration methods on Qwen3.6-27B. The data exposes which techniques preserve capability, which destroy it, and why one popular method is built on stolen code.

#abliteration#LLM Safety#model alignment...

AI ethics

Claude at War: When Your AI Safety Standards Collide with Pentagon Targeting Systems

Investigation into reports alleging Anthropic’s Claude AI is used within US military networks to prioritize targets during Middle East conflicts, raising significant ethical questions.

#AI ethics#anthropic#autonomous weapons...