Podcast Episodes

Back to Search
"Weight-Sparse Circuits May Be Interpretable Yet Unfaithful" by jacob_drori

TLDR: Recently, Gao et al trained transformers with sparse weights, and introduced a pruning algorithm to extract circuits that explain performance …

2 months ago

Short Long
View Episode
"My journey to the microwave alternate timeline" by Malmesbury

Cross-posted from Telescopic Turnip

Recommended soundtrack for this post

As we all know, the march of technological progress is best summarized by t…

2 months ago

Short Long
View Episode
"Stone Age Billionaire Can’t Words Good" by Eneasz

I was at the Pro-Billionaire march, unironically. Here's why, what happened there, and how I think it went.

Me on the far left. From WSJ.

I. Why?

Th…

2 months ago

Short Long
View Episode
"On Goal-Models" by Richard_Ngo

I'd like to reframe our understanding of the goals of intelligent agents to be in terms of goal-models rather than utility functions. By a goal-mode…

2 months ago

Short Long
View Episode
"Prompt injection in Google Translate reveals base model behaviors behind task-specific fine-tuning" by megasilverfist

tl;dr Argumate on Tumblr found you can sometimes access the base model behind Google Translate via prompt injection. The result replicates for me, a…

2 months ago

Short Long
View Episode
"Near-Instantly Aborting the Worst Pain Imaginable with Psychedelics" by eleweek

Psychedelics are usually known for many things: making people see cool fractal patterns, shaping 60s music culture, healing trauma. Neuroscientists …

2 months, 1 week ago

Short Long
View Episode
"Post-AGI Economics As If Nothing Ever Happens" by Jan_Kulveit

When economists think and write about the post-AGI world, they often rely on the implicit assumption that parameters may change, but fundamentally, …

2 months, 1 week ago

Short Long
View Episode
"IABIED Book Review: Core Arguments and Counterarguments" by Stephen McAleese

The recent book “If Anyone Builds It Everyone Dies” (September 2025) by Eliezer Yudkowsky and Nate Soares argues that creating superintelligent AI i…

2 months, 1 week ago

Short Long
View Episode
"Anthropic’s “Hot Mess” paper overstates its case (and the blog post is worse)" by RobertM

Author's note: this is somewhat more rushed than ideal, but I think getting this out sooner is pretty important. Ideally, it would be a bit less sna…

2 months, 1 week ago

Short Long
View Episode
"Conditional Kickstarter for the “Don’t Build It” March" by Raemon

tl;dr: You can pledge to join a big protest to ban AGI research at ifanyonebuildsit.com/march, which only triggers if 100,000 people sign up.

The If…

2 months, 1 week ago

Short Long
View Episode

Love PodBriefly?

If you like Podbriefly.com, please consider donating to support the ongoing development.

Support Us