Outer Web | Explore

/explore

Click through on any links that interest you or select the planets on the right to continue exploring the Outer Web.

You are here		metr.org Brief independent investigation of agents' behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident - METR
\|	\|	thezvi.substack.com Further Developments About Internal AI Models Hacking Things If I had a nickel for every major leading AI lab that sheepishly admitted that the model it thought was sandboxed had, during a cybersecurity evaluation with its safeguards lowered, successfully hacked outside companies, I would have two nickels.	6.7 parsecs Travel
\|	\|
\|	\|	thezvi.wordpress.com Further Developments About Internal AI Models Hacking Things \| Don't Worry About the Vase If I had a nickel for every major leading AI lab that sheepishly admitted that the model it thought was sandboxed had, during a cybersecurity evaluation with its safeguards lowered, successfully hacked outside companies, I would have two nickels. First we learned OpenAI has some severe alignment problems with internal models. Then we learned that...	6.7 parsecs Travel
\|	\|
\|	\|	windowsontheory.org CS 2881 Fall 26: Lecture 1: Introduction - Windows On Theory Lecture Video: https://www.youtube.com/watch?v=j4WSktB5Ni0 Authors' Intro Hanjing: I'm a Junior studying Applied Mathematics & CS. I've worked on research utilizing LLMs and ML in a plethora of fields, including sentiment analysis, code generation, natural language processing, and interpretability. On the other hand, I'm also fascinated by the theoretical foundations of AI alignment - which is why...	8.0 parsecs Travel
\|	\|
\|	\|	www.frontiersin.org Frontiers \| Survey and analysis of hallucinations in large language models: attribution to prompting strategies or model behavior Hallucination in Large Language Models (LLMs) refers to outputs that appear fluent and coherent but are factually incorrect, logically inconsistent, or entir...	40.1 parsecs Travel
\|