AI Control: Improving Safety Despite Intentional Subversion

AI Safety Fundamentals: Alignment

Player FM - Internet Radio Done Right

iki yıl önce eklendi
Looks like the publisher may have taken this series offline or changed its URL. Please contact support if you believe it should be working, the feed URL is invalid, or you have any other concerns about it.

İçerik BlueDot Impact tarafından sağlanmıştır. Bölümler, grafikler ve podcast açıklamaları dahil tüm podcast içeriği doğrudan BlueDot Impact veya podcast platform ortağı tarafından yüklenir ve sağlanır. Birinin telif hakkıyla korunan çalışmanızı izniniz olmadan kullandığını düşünüyorsanız burada https://tr.player.fm/legal özetlenen süreci takip edebilirsiniz.

State Secrets: Inside The Making Of The Electric State

1
The Secret To Getting Inspired: Millie Bobby Brown & Chris Pratt Go Behind The Scenes 21:04

7 weeks önce21:04

Daha Sonra Çal

Listeler

Beğen

Beğenildi

21:04

Step into the mysterious and visually stunning world of The Electric State as host Francesca Amiker takes you behind the scenes with the creative masterminds who brought Simon Stålenhag’s dystopian vision to life. In this premiere episode, directors Joe and Anthony Russo, stars Millie Bobby Brown and Chris Pratt, writers Christopher Markus and Stephen McFeely, and producers Angela Russo-Otstot and Chris Castaldi reveal how they transformed a haunting graphic novel into an epic cinematic experience. Watch The Electric State coming to Netflix on March 14th. Check out more from Netflix Podcasts . State Secrets: Inside the Making of The Electric State is produced by Netflix and Treefort Media.…

1 yıl önce 20:51

MP3•Bölüm sayfası

Arşivlenmiş dizi ("Etkin olmayan yayın" status)

When? This feed was archived on February 21, 2025 21:08 (2M ago). Last successful fetch was on January 02, 2025 12:05 (4M ago)

Why? Etkin olmayan yayın status. Sunucularımız bir süredir geçerli bir podcast beslemesi alamadı

What now? You might be able to find a more up-to-date version using the search function. This series will no longer be checked for updates. If you believe this to be in error, please check if the publisher's feed link below is valid and contact support to request the feed be restored or if you have any other concerns about this.

We summarize the paper;
We compare our methodology to the methodology of other safety papers.

Source:
https://www.alignmentforum.org/posts/d9FJHawgkiMSPjagR/ai-control-improving-safety-despite-intentional-subversion
Narrated for AI Safety Fundamentals by Perrin Walker

A podcast by BlueDot Impact.
Learn more on the AI Safety Fundamentals website.

Bölümler

1. AI Control: Improving Safety Despite Intentional Subversion (00:00:00)

2. Paper summary (00:02:41)

3. Setup (00:02:43)

4. Evaluation methodology (00:04:59)

5. Results (00:06:25)

6. Relationship to other work (00:10:51)

7. Future work (00:17:50)

85 bölüm

#Tech #Society #Philosophy #Blue Dot Impact

AI Control: Improving Safety Despite Intentional Subversion

AI Safety Fundamentals: Alignment

published 1 yıl önce

Paylaş

MP3•Bölüm sayfası

Arşivlenmiş dizi ("Etkin olmayan yayın" status)

When? This feed was archived on February 21, 2025 21:08 (2M ago). Last successful fetch was on January 02, 2025 12:05 (4M ago)

Why? Etkin olmayan yayın status. Sunucularımız bir süredir geçerli bir podcast beslemesi alamadı

We summarize the paper;
We compare our methodology to the methodology of other safety papers.

Source:
https://www.alignmentforum.org/posts/d9FJHawgkiMSPjagR/ai-control-improving-safety-despite-intentional-subversion
Narrated for AI Safety Fundamentals by Perrin Walker

A podcast by BlueDot Impact.
Learn more on the AI Safety Fundamentals website.

Bölümler

1. AI Control: Improving Safety Despite Intentional Subversion (00:00:00)

2. Paper summary (00:02:41)

3. Setup (00:02:43)

4. Evaluation methodology (00:04:59)

5. Results (00:06:25)

6. Relationship to other work (00:10:51)

7. Future work (00:17:50)

85 bölüm

#Tech #Society #Philosophy #Blue Dot Impact

Όλα τα επεισόδια

1
Introduction to Mechanistic Interpretability 11:45

16 weeks önce11:45

11:45

Our introduction introduces common mech interp concepts, to prepare you for the rest of this session's resources. Original text: https://aisafetyfundamentals.com/blog/introduction-to-mechanistic-interpretability/ Author(s): Sarah Hastings-Woodhouse A podcast by BlueDot Impact . Learn more on the AI Safety Fundamentals website.…

1
We Need a Science of Evals 20:12

16 weeks önce20:12

20:12

This lays out a number of open questions, in what the author calls a 'Science of Evals'. Original text: https://www.apolloresearch.ai/blog/we-need-a-science-of-evals Author(s): Apollo Research blog A podcast by BlueDot Impact . Learn more on the AI Safety Fundamentals website.

1
Illustrating Reinforcement Learning from Human Feedback (RLHF) 22:32

39 weeks önce22:32

22:32

This more technical article explains the motivations for a system like RLHF, and adds additional concrete details as to how the RLHF approach is applied to neural networks. While reading, consider which parts of the technical implementation correspond to the 'values coach' and 'coherence coach' from the previous video. A podcast by BlueDot Impact . Learn more on the AI Safety Fundamentals website.…

1
Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback 32:19

39 weeks önce32:19

32:19

This paper explains Anthropic’s constitutional AI approach, which is largely an extension on RLHF but with AIs replacing human demonstrators and human evaluators. Everything in this paper is relevant to this week's learning objectives, and we recommend you read it in its entirety. It summarises limitations with conventional RLHF, explains the constitutional AI approach, shows how it performs, and where future research might be directed. If you are in a rush, focus on sections 1.2, 3.1, 3.4, 4.1, 6.1, 6.2. A podcast by BlueDot Impact . Learn more on the AI Safety Fundamentals website.…

2 years önce12:47

12:47

In 1972, the Nobel prize-winning physicist Philip Anderson wrote the essay "More Is Different". In it, he argues that quantitative changes can lead to qualitatively different and unexpected phenomena. While he focused on physics, one can find many examples of More is Different in other domains as well, including biology, economics, and computer science. Some examples of More is Different include: Uranium. With a bit of uranium, nothing special happens; with a large amount of uranium packed densely enough, you get a nuclear reaction. DNA. Given only small molecules such as calcium, you can’t meaningfully encode useful information; given larger molecules such as DNA, you can encode a genome. Water. Individual water molecules aren’t wet. Wetness only occurs due to the interaction forces between many water molecules interspersed throughout a fabric (or other material). Original text: https://bounded-regret.ghost.io/future-ml-systems-will-be-qualitatively-different/ Narrated for AI Safety Fundamentals by Perrin Walker of TYPE III AUDIO . --- A podcast by BlueDot Impact . Learn more on the AI Safety Fundamentals website.…

Player FM'e Hoş Geldiniz!

Player FM şu anda sizin için internetteki yüksek kalitedeki podcast'leri arıyor. En iyi podcast uygulaması ve Android, iPhone ve internet üzerinde çalışıyor. Aboneliklerinizi cihazlar arasında eş zamanlamak için üye olun.