Podcast Episodes

“There are only four skills: design, technical, management and physical” by habryka

Epistemic status: Completely schizo galaxy-brained theory

Lightcone[1] operates on a "generalist" philosophy. Most of our full-time staff have the t…

2 days, 22 hours ago

“Having OCD is like living in North Korea (Here’s how I escaped)” by Declan Molony

[Author's note: this post is the narrative version that explains my journey with OCD and how I treated it. The short version provides quick, actiona…

3 days, 4 hours ago

“Claude knows who you are” by Smaug123

Kelsey Piper noticed that Opus 4.7 is the first model which can identify her from her unpublished writing.

I replicated the experiment myself, which…

3 days, 10 hours ago

“Vladimir Putin’s CEV is probably pretty good” by habryka

(Written quickly for Inkhaven, I hope someone someday makes a better case for this than I will here)

Kelsey Piper on Twitter:

me: it's not okay to …

3 days, 11 hours ago

“Post-mortem’ing my earliest ML research paper, 7 years later” by LawrenceC

Written quickly for the Inkhaven Residency.

One of the things I like most about LessWrong yearly reviews is that they occur a full year after: for e…

3 days, 13 hours ago

“If You’ve Never Bought a Tool You Didn’t Need, You’re Not Buying Enough Tools” by Drake Morrison

Having more tools greatly increases the space of potential plans you can consider. So by default you should be getting more tools. Having too few to…

3 days, 18 hours ago

“3” by AnnaJo

Warning: This is completely based on my own experiences; please do your own research before trying different types of birth control.

TL;DR: Sex horm…

4 days, 2 hours ago

“Consent-Based RL: Letting Models Endorse Their Own Training Updates” by Logan Riggs

AKA scalable oversight of value drift

TL;DR LLMs could be aligned but then corrupted through RL, instrumentally converging on deep consequentialism.…

4 days, 4 hours ago

“Prompted CoT Early Exit Undermines the Monitoring Benefits of CoT Uncontrollability” by Elle Najt, Asa Cooper Stickland, Xander Davies

Code: github.com/ElleNajt/controllability

tldr:

Yueh-Han et al. (2026) showed that models have a harder time making their chain of thought follow …

4 days, 6 hours ago

“AI #164: Pre Opus” by Zvi

This is a day late because, given the discourse around Dwarkesh Patel's interview with Jensen Huang, I pushed the weekly to Friday.

This week's cov…

4 days, 10 hours ago