Redwood Research Blog

Redwood Research Blog

Por: Redwood Research
Narrations of Redwood Research blog posts.

Redwood Research is a research nonprofit based in Berkeley. We investigate risks posed by the development of powerful artificial intelligence and techniques for mitigating those risks.
82 episodios disponibles

Latest episodes of the podcast Redwood Research Blog

The inaugural Redwood Research podcast 06/01/2026
“Recent LLMs can do 2-hop and 3-hop latent (no CoT) reasoning on natural facts” by Ryan Greenblatt 01/01/2026
“Measuring no CoT math time horizon (single forward pass)” by Ryan Greenblatt 26/12/2025
“Recent LLMs can use filler tokens or problem repeats to improve (no-CoT) math performance” by Ryan Greenblatt 22/12/2025
“BashArena and Control Setting Design” by Adam Kaufman, jlucassen 18/12/2025
“The behavioral selection model for predicting AI motivations” by Alex Mallen, Buck Shlegeris 04/12/2025
“Will AI systems drift into misalignment?” by Josh Clymer 15/11/2025
“What’s up with Anthropic predicting AGI by early 2027?” by Ryan Greenblatt 03/11/2025
“Sonnet 4.5’s eval gaming seriously undermines alignment evals” by Alexa Pan, Ryan Greenblatt 30/10/2025
“Should AI Developers Remove Discussion of AI Misalignment from AI Training Data?” by Alek Westover 23/10/2025
“Is 90% of code at Anthropic being written by AIs?” by Ryan Greenblatt 22/10/2025
“Reducing risk from scheming by studying trained-in scheming behavior” by Ryan Greenblatt 16/10/2025
“Iterated Development and Study of Schemers (IDSS)” by Ryan Greenblatt 10/10/2025
“The Thinking Machines Tinker API is good news for AI control and security” by Buck Shlegeris 09/10/2025
“Plans A, B, C, and D for misalignment risk” by Ryan Greenblatt 08/10/2025
“Notes on fatalities from AI takeover” by Ryan Greenblatt 23/09/2025
“Focus transparency on risk reports, not safety cases” by Ryan Greenblatt 22/09/2025
“Prospects for studying actual schemers” by Ryan Greenblatt, Julian Stastny 19/09/2025
“What training data should developers filter to reduce risk from misaligned AI?” by Alek Westover 17/09/2025
“AIs will greatly change engineering in AI companies well before AGI” by Ryan Greenblatt 09/09/2025
1 2 3 ... 5 Siguiente › Última »
© 2003-2026 ZARZA | AHEAD OF OUR TIME
privacy policy
In God we trust In God we trust
PreSales Questions? Click Here
or call our toll-free line at +1-888-5002068 Miami, Florida, USA