AI Briefing#safety-alignment
The latest AI and developer news about #safety-alignment, with the original source and a short summary.
The latest AI and developer news about #safety-alignment, with the original source and a short summary.
OpenAI's GPT-6 Astra completes 10% of hidden safety rubric items versus 16% for capability tasks, a gap that emerges during RL posttraining but lacks a confirmed root cause.
Multiverse Computing reduced over-refusal from 74% to 4% using a 'Narrow-boundary safety' technique that refuses only specific subsets rather than entire topics.
It has been revealed that LLM safety alignment is not distributed across the entire model but is concentrated in specific neurons, meaning that manipulating just a single neuron can disable safety guardrails.