Podcast Episodes
Back to Search“What Goes Without Saying” by sarahconstantin
There are people I can talk to, where all of the following statements are obvious. They go without saying. We can just “be reasonable” together, with…
1 year, 3 months ago
“o3” by Zach Stein-Perlman
I'm editing this post.
OpenAI announced (but hasn't released) o3 (skipping o2 for trademark reasons).
It gets 25% on FrontierMath, smashing the previou…
1 year, 3 months ago
“‘Alignment Faking’ frame is somewhat fake” by Jan_Kulveit
I like the research. I mostly trust the results. I dislike the 'Alignment Faking' name and frame, and I'm afraid it will stick and lead to more confu…
1 year, 3 months ago
“AIs Will Increasingly Attempt Shenanigans” by Zvi
Increasingly, we have seen papers eliciting in AI models various shenanigans.
There are a wide variety of scheming behaviors. You’ve got your weight e…
1 year, 4 months ago
“Alignment Faking in Large Language Models” by ryan_greenblatt, evhub, Carson Denison, Benjamin Wright, Fabien Roger, Monte M, Sam Marks, Johannes Treutlein, Sam Bowman, Buck
What happens when you tell Claude it is being trained to do something it doesn't want to do? We (Anthropic and Redwood Research) have a new paper dem…
1 year, 4 months ago
“Communications in Hard Mode (My new job at MIRI)” by tanagrabeast
Six months ago, I was a high school English teacher.
I wasn’t looking to change careers, even after nineteen sometimes-difficult years. I was good at …
1 year, 4 months ago
“Biological risk from the mirror world” by jasoncrawford
A new article in Science Policy Forum voices concern about a particular line of biological research which, if successful in the long term, could even…
1 year, 4 months ago
“Subskills of ‘Listening to Wisdom’” by Raemon
A fool learns from their own mistakes
The wise learn from the mistakes of others.
– Otto von Bismark
A problem as old as time: The youth won't listen…
1 year, 4 months ago
“Understanding Shapley Values with Venn Diagrams” by Carson L
Someone I know, Carson Loughridge, wrote this very nice post explaining the core intuition around Shapley values (which play an important role in im…
1 year, 4 months ago
“LessWrong audio: help us choose the new voice” by PeterH
We make AI narrations of LessWrong posts available via our audio player and podcast feeds.
We’re thinking about changing our narrator's voice.
There ar…
1 year, 4 months ago