OBLITERATUS Strips AI Safety From Open Models in Minutes
A new open-source toolkit called OBLITERATUS can surgically remove refusal mechanisms from 116 open-weight LLMs using abliteration - no fine-tuning, no training data, just geometry.
Llms
LLMs Can Unmask Online Users for $4, Study Finds
Researchers from ETH Zurich and Anthropic show that LLM agents can strip pseudonymity from forum posts at scale for as little as $1.41 per target - matching what human investigators could do in hours.
What Are AI Reasoning Models?
A plain-English guide to AI reasoning models - what they are, how they think step by step, and when you should actually use one.
A Nature Paper Says AGI Is Already Here - Not Everyone Agrees
Four UC San Diego researchers argue in Nature that current LLMs already constitute artificial general intelligence, igniting fierce debate across the AI community.
