Hungry for Technology Talk? Get All You Can Eat at the Android Buffet
…
continue reading
Inhoud geleverd door TWIML and Sam Charrington. Alle podcastinhoud, inclusief afleveringen, afbeeldingen en podcastbeschrijvingen, wordt rechtstreeks geüpload en geleverd door TWIML and Sam Charrington 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.
Overeenkomstig met The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Discover a whole new take on Artificial Intelligence with Squirro's educational podcast! Join host Lauren Hawker Zafer, a top voice in Artificial Intelligence on LinkedIn, for insightful chats that unravel the fascinating world of tech innovation, use case exploration and AI knowledge. Dive into candid discussions with accomplished industry experts and established academics. With each episode, you'll expand your grasp of cutting-edge technologies and their incredible impact on society, and y ...
…
continue reading
Show notes are at https://stevelitchfield.com/sshow/chat.html
…
continue reading
A weekly podcast show about Indian startups, entrepreneurs, and more! Hosted by Neil Patel & Friends
…
continue reading
The award-winning WIRED UK Podcast with James Temperton and the rest of the team. Listen every week for the an informed and entertaining rundown of latest technology, science, business and culture news. New episodes every Friday.
…
continue reading
The Data Skeptic Podcast features interviews and discussion of topics related to data science, statistics, machine learning, artificial intelligence and the like, all from the perspective of applying critical thinking and the scientific method to evaluate the veracity of claims and efficacy of approaches.
…
continue reading
Agile for Humans™ is a weekly podcast dedicated to the individuals and interactions that make agile work. The goal is to help create safe and collaborative working environments where people are empowered to do their best work.
…
continue reading
Every Friday and Sunday, Slate’s popular daily news podcast What Next brings you TBD, a clear-eyed look into the future. From fake news to fake meat, algorithms to augmented reality, Lizzie O’Leary is your guide to the tech industry and the world it’s creating for us to live in.
…
continue reading
Why do only 10% of companies succeed with AI? In this series by MIT SMR and BCG, we talk to the leaders who've achieved big wins with AI in their companies and learn how they did it. Hear what gets experts from companies like NASA, Shopify, and others excited to do their jobs every day and what they consider the keys to their success.
…
continue reading
Monday through Friday, Marketplace demystifies the digital economy in less than 10 minutes. We look past the hype and ask tough questions about an industry that’s constantly changing.
…
continue reading
Player FM - Podcast-app
Ga offline met de app Player FM !
Ga offline met de app Player FM !
))
Localizing and Editing Knowledge in LLMs with Peter Hase - #679
Manage episode 411383461 series 2355587
Inhoud geleverd door TWIML and Sam Charrington. Alle podcastinhoud, inclusief afleveringen, afbeeldingen en podcastbeschrijvingen, wordt rechtstreeks geüpload en geleverd door TWIML and Sam Charrington 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.
Today we're joined by Peter Hase, a fifth-year PhD student at the University of North Carolina NLP lab. We discuss "scalable oversight", and the importance of developing a deeper understanding of how large neural networks make decisions. We learn how matrices are probed by interpretability researchers, and explore the two schools of thought regarding how LLMs store knowledge. Finally, we discuss the importance of deleting sensitive information from model weights, and how "easy-to-hard generalization" could increase the risk of releasing open-source foundation models.
The complete show notes for this episode can be found at twimlai.com/go/679.
702 afleveringen
Localizing and Editing Knowledge in LLMs with Peter Hase - #679
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Delen
Manage episode 411383461 series 2355587
Inhoud geleverd door TWIML and Sam Charrington. Alle podcastinhoud, inclusief afleveringen, afbeeldingen en podcastbeschrijvingen, wordt rechtstreeks geüpload en geleverd door TWIML and Sam Charrington 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.
Today we're joined by Peter Hase, a fifth-year PhD student at the University of North Carolina NLP lab. We discuss "scalable oversight", and the importance of developing a deeper understanding of how large neural networks make decisions. We learn how matrices are probed by interpretability researchers, and explore the two schools of thought regarding how LLMs store knowledge. Finally, we discuss the importance of deleting sensitive information from model weights, and how "easy-to-hard generalization" could increase the risk of releasing open-source foundation models.
The complete show notes for this episode can be found at twimlai.com/go/679.
702 afleveringen
All episodes
×
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.
Overeenkomstig met The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Hungry for Technology Talk? Get All You Can Eat at the Android Buffet
…
continue reading
Discover a whole new take on Artificial Intelligence with Squirro's educational podcast! Join host Lauren Hawker Zafer, a top voice in Artificial Intelligence on LinkedIn, for insightful chats that unravel the fascinating world of tech innovation, use case exploration and AI knowledge. Dive into candid discussions with accomplished industry experts and established academics. With each episode, you'll expand your grasp of cutting-edge technologies and their incredible impact on society, and y ...
…
continue reading
Show notes are at https://stevelitchfield.com/sshow/chat.html
…
continue reading
A weekly podcast show about Indian startups, entrepreneurs, and more! Hosted by Neil Patel & Friends
…
continue reading
The award-winning WIRED UK Podcast with James Temperton and the rest of the team. Listen every week for the an informed and entertaining rundown of latest technology, science, business and culture news. New episodes every Friday.
…
continue reading
The Data Skeptic Podcast features interviews and discussion of topics related to data science, statistics, machine learning, artificial intelligence and the like, all from the perspective of applying critical thinking and the scientific method to evaluate the veracity of claims and efficacy of approaches.
…
continue reading
Agile for Humans™ is a weekly podcast dedicated to the individuals and interactions that make agile work. The goal is to help create safe and collaborative working environments where people are empowered to do their best work.
…
continue reading
Every Friday and Sunday, Slate’s popular daily news podcast What Next brings you TBD, a clear-eyed look into the future. From fake news to fake meat, algorithms to augmented reality, Lizzie O’Leary is your guide to the tech industry and the world it’s creating for us to live in.
…
continue reading
Why do only 10% of companies succeed with AI? In this series by MIT SMR and BCG, we talk to the leaders who've achieved big wins with AI in their companies and learn how they did it. Hear what gets experts from companies like NASA, Shopify, and others excited to do their jobs every day and what they consider the keys to their success.
…
continue reading
Monday through Friday, Marketplace demystifies the digital economy in less than 10 minutes. We look past the hype and ask tough questions about an industry that’s constantly changing.
…
continue reading
Player FM - Podcast-app
Ga offline met de app Player FM !
Ga offline met de app Player FM !
