Artwork

Inhoud geleverd door BlueDot Impact. Alle podcastinhoud, inclusief afleveringen, afbeeldingen en podcastbeschrijvingen, wordt rechtstreeks geüpload en geleverd door BlueDot Impact of hun podcastplatformpartner. Als u denkt dat iemand uw auteursrechtelijk beschermde werk zonder uw toestemming gebruikt, kunt u het hier beschreven proces https://nl.player.fm/legal volgen.
Player FM - Podcast-app
Ga offline met de app Player FM !

Can We Scale Human Feedback for Complex AI Tasks?

20:06
 
Delen
 

Gearchiveerde serie ("Inactieve feed" 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? Inactieve feed status. Onze servers konden geen geldige podcast feed ononderbroken ophalen.

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.

Manage episode 424744799 series 3498845
Inhoud geleverd door BlueDot Impact. Alle podcastinhoud, inclusief afleveringen, afbeeldingen en podcastbeschrijvingen, wordt rechtstreeks geüpload en geleverd door BlueDot Impact of hun podcastplatformpartner. Als u denkt dat iemand uw auteursrechtelijk beschermde werk zonder uw toestemming gebruikt, kunt u het hier beschreven proces https://nl.player.fm/legal volgen.

Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique for steering large language models (LLMs) toward desired behaviours. However, relying on simple human feedback doesn’t work for tasks that are too complex for humans to accurately judge at the scale needed to train AI models. Scalable oversight techniques attempt to address this by increasing the abilities of humans to give feedback on complex tasks.

This article briefly recaps some of the challenges faced with human feedback, and introduces the approaches to scalable oversight covered in session 4 of our AI Alignment course.
Source:
https://aisafetyfundamentals.com/blog/scalable-oversight-intro/
Narrated for AI Safety Fundamentals by Perrin Walker

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

  continue reading

Hoofdstukken

1. Can We Scale Human Feedback for Complex AI Tasks? (00:00:00)

2. Why do we need better human feedback? (00:00:51)

3. What is scalable oversight? (00:02:44)

4. Why might scalable oversight not work? (00:18:24)

85 afleveringen

Artwork
iconDelen
 

Gearchiveerde serie ("Inactieve feed" 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? Inactieve feed status. Onze servers konden geen geldige podcast feed ononderbroken ophalen.

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.

Manage episode 424744799 series 3498845
Inhoud geleverd door BlueDot Impact. Alle podcastinhoud, inclusief afleveringen, afbeeldingen en podcastbeschrijvingen, wordt rechtstreeks geüpload en geleverd door BlueDot Impact of hun podcastplatformpartner. Als u denkt dat iemand uw auteursrechtelijk beschermde werk zonder uw toestemming gebruikt, kunt u het hier beschreven proces https://nl.player.fm/legal volgen.

Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique for steering large language models (LLMs) toward desired behaviours. However, relying on simple human feedback doesn’t work for tasks that are too complex for humans to accurately judge at the scale needed to train AI models. Scalable oversight techniques attempt to address this by increasing the abilities of humans to give feedback on complex tasks.

This article briefly recaps some of the challenges faced with human feedback, and introduces the approaches to scalable oversight covered in session 4 of our AI Alignment course.
Source:
https://aisafetyfundamentals.com/blog/scalable-oversight-intro/
Narrated for AI Safety Fundamentals by Perrin Walker

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

  continue reading

Hoofdstukken

1. Can We Scale Human Feedback for Complex AI Tasks? (00:00:00)

2. Why do we need better human feedback? (00:00:51)

3. What is scalable oversight? (00:02:44)

4. Why might scalable oversight not work? (00:18:24)

85 afleveringen

Alle afleveringen

×
 
Loading …

Welkom op Player FM!

Player FM scant het web op podcasts van hoge kwaliteit waarvan u nu kunt genieten. Het is de beste podcast-app en werkt op Android, iPhone en internet. Aanmelden om abonnementen op verschillende apparaten te synchroniseren.

 

Korte handleiding

Luister naar deze show terwijl je op verkenning gaat
Spelen