Sveriges mest populära poddar

Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback

32 min•4 januari 2025

Audio versions of blogs and papers from BlueDot courses.

This paper explains Anthropic’s constitutional AI approach, which is largely an extension on RLHF but with AIs replacing human demonstrators and human evaluators.

A podcast by BlueDot Impact.

Fler avsnitt av BlueDot Narrated

Far-UVC

16 jan.•7 min

Innovate and Stockpile: Respiratory Protection for Essential Workers in a Catastrophic Pandemic

15 jan.•21 min

Flipping the switch on far-UVC

15 jan.•6 min

What is AI Alignment?

15 jan.•19 min

What Are the Odds H5N1 Is Worse Than COVID-19

12 jan.•15 min

Scaling US Pathogen Detection

5 jan.•21 min

Do the Biorisk Evaluations of AI Labs Actually Measure the Risk of Developing Bioweapons?

5 jan.•33 min

The Four Pillars: A Hypothesis for Countering Catastrophic Biological Risk

5 jan.•30 min

Risk and Benefit Analysis of Gain of Function Research

21 dec. 2025•30 min

How to stop bioterrorists from buying dangerous DNA

21 dec. 2025•14 min

BlueDot Narrated med BlueDot Impact finns tillgänglig på flera plattformar. Informationen på denna sida kommer från offentliga podd-flöden.