Why is o1 so deceptive?
Published on September 27, 2024 5:27 PM GMT The o1 system card reports: 0.8% of o1-preview’s responses got flagged as ...
Read more
The Download: Safer space travel, and generative AI in video games
Long-distance space travel can wreak havoc on human health. There’s radiation and microgravity to contend with, as well as the ...
Read more
An open response to Wittkotter and Yampolskiy — AI Alignment Forum
A response to this paper. https://asi-safety-lab.com/DL/Kill-Switch-For_ASI_EW_21_12_14.pdf A substantial fraction of my argument comes down to. It is plausible that a ...
Read more
Why Microsoft made a deal to help restart Three Mile Island
That nuclear power plant is typically associated with a very specific event. One of its reactors, Unit 2, suffered a ...
Read more
How to prevent collusion when using untrusted models to monitor each other — AI Alignment Forum
Suppose you’ve trained a really clever AI model, and you’re planning to deploy it in an agent scaffold that allows ...
Read more
The Download: How to connect the US’s grids, and OpenAI’s new voice mode
Michael Skelly hasn’t learned to take no for an answer. For much of the last 15 years, the energy entrepreneur ...
Read more
/cdn.vox-cdn.com/uploads/chorus_asset/file/25212017/c_ASALOON.png?w=150&resize=150,150&ssl=1 "Honda has a plan to build solid-state batteries for EVs")
