Audio narrations of LessWrong posts.
Open Philanthropy has just launched a large new Request for Proposals for technical AI safety resear
Racing Towards a New Technology Is a Collective Choice, Not an Inevitable Consequence of Incentives
Once upon a time, in ye olden days of strange names and before google maps, seven friends needed to
I’m not a natural “doomsayer.” But unfortunately, part of my job as an AI safety researcher is to t
This is a link post. Open Philanthropy Technical AI Safety RFP - $40M Available Across 21 Research A
I've just opened summer MATS applications (where I'll supervise people to write mech interp papers)
This is a link post.Can you tell when an LLM is lying from the activations? Are simple methods good
The votes are in for the 2023 Review!6,264 posts were written in 2023. 662 of them got at least one
The baseline scenario as AI becomes AGI becomes ASI (artificial superintelligence), if nothing more
I'm writing a more in-depth review of the State of Feedbackloop Rationality. (I've written a short r
This is a link post.I haven't looked into this in detail, and I'm not actually sure how unique a sit
Audio note: this article contains 55 uses of latex notation, so the narration may be difficult to
Audio note: this article contains 182 uses of latex notation, so the narration may be difficult to
Yeah I put this off until the last day, and I'm not sure this is the format Raemon was actually look
The latest addition to OpenAI's Pro offerings is their version of Deep Research. Have you longed fo
This is a link post.Meta just published its version of an RSP (blogpost, framework).(Expect several
In his recent post arguing against AI Control research, John Wentworth argues that the median doom p
I love the Burren. It hosts something like seven weekly sessions in a range of styles and the b
New model, new hype cycle, who dis? On a Friday afternoon, OpenAI was proud to announce the new mode
This is a link post.Today we’re launching deep research in ChatGPT, a new agentic capability that co
