Recursive forecasting: Eliciting long-term forecasts from myopic fitness-seekers
We’d like to use powerful AIs to answer questions that may take a long time…
Category: Opinion
Sleeper Agent Backdoor Results Are Messy
TL;DR: We replicated the Sleeper Agents (SA) setup with Llama-3.3-70B and Llama-3.1-8B, training models to repeatedly…
Forecasting is Not Overrated and It’s Probably Funded Appropriately
(A response to @mabramov post from a couple days ago: https://www.lesswrong.com/posts/WCutvyr9rr3cpF6hx/forecasting-is-way-overrated-and-we-should-stop-funding-it )TL;DR: I agree with…
Microsoft AI CEO’s “Seemingly Conscious AI Risk”
Microsoft CEO Mustafa Suleyman recently co-authored a paper called "Seemingly Conscious AI Risk".I was pretty…
LessWrong Shows You Social Signals Before the Comment
When reading a comment, the first thing you see is what other people think. That…
Fail safe(r) at alignment by channeling reward-hacking into a “spillway” motivation
It's plausible that flawed RL processes will select for misaligned AI motivations.[1] Some misaligned motivations…
Update on the Alex Bores campaign
In October, I wrote a post arguing that donating to Alex Bores's campaign for Congress…
GPT 5.5: The System Card
Last week, OpenAI announced GPT-5.5, including GPT-5.5-Pro. My overall read here is that GPT-5.5 is…
AI companies should publish security assessments
AI companies should get third-party security experts to assess (and possibly also red-team/pen-test) their security…
In defense of parents
Contra Aella on chattel childhoodAella has a post where she argues that today's parents don't…