Podcast Episodes

Back to Search
“Announcing our $160M grant from Coefficient Giving” by Geoffrey Irving, Jesse Hoogland, Alex HT, Jacob Pfau, Daniel Murfet, Marco Cozzi, Stan van Wingerden

We are excited to announce that Resolution (fka Sequent) has a 160 million dollars grant from Coefficient Giving (cG) to put rigorous alignment rese…

3 weeks, 2 days ago

Short Long
View Episode
“Because 8 ≈ e², Anthropic’s researcher uplift is plausibly >2x” by Thomas Kwa

Note: the modeling assumptions and conclusion are Thomas Kwa's opinion, and others at METR disagree. [1] Also, the math was checked by Claude but n…

3 weeks, 2 days ago

Short Long
View Episode
“Optimiser Choice Can Amplify or Suppress Emergent Misalignment” by Jason R Brown, Patrick Leask, Lev McKinney

This is a linkpost for https://arxiv.org/abs/2606.31591. Work done with Patrick Leask and Lev McKinney during the Astra Fellowship.

TL;DR: Optimiser…

3 weeks, 2 days ago

Short Long
View Episode
“Childhood and Education #20: Phones and Screens” by Zvi

We have a respite, so I thought I’d tackle various thoughts on children, phones and screens. GPT-5.6-Sol drops tomorrow, and the Fable agents are ha…

3 weeks, 2 days ago

Short Long
View Episode
“How slower does takeoff go with 10× less compute?” by bhalstead

About 6x slower in the median case, with an 80% confidence interval of 3.5x to 8x.

Setup

Define the "R&D compute" (in, say, H100-equivalents) of an…

3 weeks, 2 days ago

Short Long
View Episode
“Find funding, fast” by Austin Chen

Some AI safety funders can take months to decide; others confirm in days. I’ve been on both sides of the grant application and know how crucial an e…

3 weeks, 3 days ago

Short Long
View Episode
“Modular Pretraining Enables Access Control” by E.Roland, cloud

Full author list: Ethan Roland*, Murat Cubuktepe*, Erick Martinez*, Stijn Servaes, Keenan Pepper, Mike Vaiana, Diogo Schwerz de Lucena, Judd Rosenbl…

3 weeks, 3 days ago

Short Long
View Episode
“Subliminal Learning Happens at Every Rank, Given the Right Learning Rate and Enough Data” by Lawrence Feng

Subliminal learning is the phenomenon where a language model picks up a behavioral trait—such as fondness for cats—by training on data from a trait-…

3 weeks, 3 days ago

Short Long
View Episode
“Why study proto-training gaming as an adversarial alignment failure mode?” by Puria, Edward James Young, Cam

This is a dual post that lays out our current research project where we compare different pre-RL alignment methods and their ability to prevent mode…

3 weeks, 3 days ago

Short Long
View Episode
“Why study alignment interventions on pre-RL checkpoints?” by Edward James Young, Puria, Cam

This is a dual post that lays out our current research project where we compare pre-RL-training methods on their ability to prevent models from ‘pro…

3 weeks, 3 days ago

Short Long
View Episode

Love PodBriefly?

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

Support Us