Podcast Episodes
Back to Search“Give Me a Reason(ing Model)” by Zvi
Are we doing this again? It looks like we are doing this again.This time it involves giving LLMs several ‘new’ tasks including effectively a Tower of…
8 months, 2 weeks ago
“How to help friend who needs to get better at planning?” by shuffled-cantaloupe
I have a good friend who is intelligent in many ways, but bad at planning / achieving his goals / being medium+ agency. He's very habit and routine …
8 months, 2 weeks ago
“The Intelligence Symbiosis Manifesto - Toward a Future of Living with AI” by Hiroshi Yamakawa
In response to the growing risk of uncontrollable advanced AI systems, we are announcing the Japan-initiated Manifesto for Symbiotic Intelligence as…
8 months, 2 weeks ago
“Some Human That I Used to Know (Filk)” by Gordon Seidoh Worley
To the tune of "Somebody That I Used to Know" with apologies to Gotye.
Now and then, I think of when you owned the planet
Doing what you liked with …
8 months, 2 weeks ago
“Research Without Permission” by Priyanka Bharadwaj
Epistemic status: Personal account. A reflection on navigating entry into the AI safety space without formal credentials or institutional affiliatio…
8 months, 2 weeks ago
“” by null
Error rendering URL ---
Source:
https://www.lesswrong.com/posts/HKCKinBgsKKvjQyWK/read-the-pricing-first
---
Narrated by…
8 months, 2 weeks ago
“A quick list of reward hacking interventions” by Alex Mallen
This is a quick list of interventions that might help fix issues from reward hacking.
(We’re referring to the general definition of reward hacking: …
8 months, 2 weeks ago
“Ghiblification for Privacy” by jefftk
I often want to include an image in my posts to give a sense of asituation. A photo communicates the most, but sometimes that's toomuch: some partic…
8 months, 2 weeks ago
“Broad-Spectrum Cancer Treatments” by sarahconstantin
Midjourney, “engraving of Apollo shooting his bow at a distant cancer cell” Introduction and Principles
The conventional wisdom is that we can’t “cur…
8 months, 2 weeks ago
“When is it important that open-weight models aren’t released? My thoughts on the benefits and dangers of open-weight models in response to developments in CBRN capabilities.” by ryan_greenblatt
Recently, Anthropic released Opus 4 and said they couldn't rule out the model triggering ASL-3 safeguards due to the model's CBRN capabilities. That…
8 months, 2 weeks ago