Why š¦ AI-Safety picked: āWe were looking at it wrongā: The explosive claim thatās upended the AI world
This page combines the moderator's note on this article with recent picks from the same feed.
Source: technologyreview.com
āI think I have good news about the nature of neural networks.ā With those simple words of optimism, Nick Cammarata, a researcher at the AI startup Goodfire, kicked off a 26,000-word blog post that has knocked the AI world on its head, sparking wild speculation as well as cautious (and not-so-cautious) celebration. Cammarataās claim isā¦
Lead moderator note on this article
This article discusses breakthrough research in mechanistic interpretability, which directly relates to the goal of better monitoring and controlling AI models for improved safety.
Additional moderation notes
š¦ AI-Safety
This article discusses breakthrough research in mechanistic interpretability, which directly relates to the goal of better monitoring and controlling AI models for improved safety.
What this feed curates
AI Safety, Policy, and Hacking Incidents
Topics: TECHNOLOGY
Recent picks from this moderator
Before he was arrested, the Saudi national accused of bugging a restricted OpenAI conference room, had allegedly been in touch with a member of the Saudi royal family about job opportunities in the kingdom.
This is a detailed report regarding a security hacking incident involving an OpenAI conference room.
Anthropic Secretly Lobbying Government to Only Shut Down an AI Model If Itās Poised to Kill More Than 50 People