Audio narrations of LessWrong posts.
Epistemic status: This post aims at an ambitious target: improving intuitive understanding directly
Gemini 2.5 Pro Experimental is America's next top large language model. That doesn’t mean it is th
What if they released the new best LLM, and almost no one noticed? Google seems to have pulled tha
The other day I discussed how high monitoring costs can explain the emergence of “aristocratic” sys
[This is our blog post on the papers, which can be found at https://transformer-circuits.pub/2025/a
At EA Global Boston last year I gave a talk on how we're in the third wave of EA/AI safety, and how
Summary We wanted to briefly share an early takeaway from our exploration into alignment faking: th
This is a link post. Summary: CLR is hiring for our Summer Research Fellowship. Join us for eight we
Selective listening is a real problem. It's really hard to listen to someone when you think you alr
Twitter thread here. tl;dr When prompted, current models can sandbag ML experiments and research de
Audio note: this article contains 31 uses of latex notation, so the narration may be difficult to
Epistemic status: Reasonably confident in the basic mechanism. Have you noticed that you keep encou
I’ve spent the past 7 years living in the DC area. I moved out there from the Pacific Northwest to
Audio note: this article contains 127 uses of latex notation, so the narration may be difficult to
This is a link post. Download the latest PDF with links to court dockets here. --- First
In this post, I'll list all the areas of control research (and implementation) that seem promising
We recently released Subversion Strategy Eval: Can language models statelessly strategize to subver
Last week I covered Anthropic's relatively strong submission, and OpenAI's toxic submission. This w
Ben Thompson interviewed Sam Altman recently about building a consumer tech company, and about the h
It seems the company has gone bankrupt and wants to be bought and you can probably get their data i
