Artwork

Kandungan disediakan oleh Daniel Filan. Semua kandungan podcast termasuk episod, grafik dan perihalan podcast dimuat naik dan disediakan terus oleh Daniel Filan atau rakan kongsi platform podcast mereka. Jika anda percaya seseorang menggunakan karya berhak cipta anda tanpa kebenaran anda, anda boleh mengikuti proses yang digariskan di sini https://ms.player.fm/legal.
Player FM - Aplikasi Podcast
Pergi ke luar talian dengan aplikasi Player FM !

16 - Preparing for Debate AI with Geoffrey Irving

1:04:49
 
Kongsi
 

Manage episode 333232020 series 2844728
Kandungan disediakan oleh Daniel Filan. Semua kandungan podcast termasuk episod, grafik dan perihalan podcast dimuat naik dan disediakan terus oleh Daniel Filan atau rakan kongsi platform podcast mereka. Jika anda percaya seseorang menggunakan karya berhak cipta anda tanpa kebenaran anda, anda boleh mengikuti proses yang digariskan di sini https://ms.player.fm/legal.

Many people in the AI alignment space have heard of AI safety via debate - check out AXRP episode 6 (axrp.net/episode/2021/04/08/episode-6-debate-beth-barnes.html) if you need a primer. But how do we get language models to the stage where they can usefully implement debate? In this episode, I talk to Geoffrey Irving about the role of language models in AI safety, as well as three projects he's done that get us closer to making debate happen: using language models to find flaws in themselves, getting language models to back up claims they make with citations, and figuring out how uncertain language models should be about the quality of various answers.

Topics we discuss, and timestamps:

- 00:00:48 - Status update on AI safety via debate

- 00:10:24 - Language models and AI safety

- 00:19:34 - Red teaming language models with language models

- 00:35:31 - GopherCite

- 00:49:10 - Uncertainty Estimation for Language Reward Models

- 01:00:26 - Following Geoffrey's work, and working with him

The transcript: axrp.net/episode/2022/07/01/episode-16-preparing-for-debate-ai-geoffrey-irving.html

Geoffrey's twitter: twitter.com/geoffreyirving

Research we discuss:

- Red Teaming Language Models With Language Models: arxiv.org/abs/2202.03286

- Teaching Language Models to Support Answers with Verified Quotes, aka GopherCite: arxiv.org/abs/2203.11147

- Uncertainty Estimation for Language Reward Models: arxiv.org/abs/2203.07472

- AI Safety via Debate: arxiv.org/abs/1805.00899

- Writeup: progress on AI safety via debate: lesswrong.com/posts/Br4xDbYu4Frwrb64a/writeup-progress-on-ai-safety-via-debate-1

- Eliciting Latent Knowledge: ai-alignment.com/eliciting-latent-knowledge-f977478608fc

- Training Compute-Optimal Large Language Models, aka Chinchilla: arxiv.org/abs/2203.15556

  continue reading

42 episod

Artwork
iconKongsi
 
Manage episode 333232020 series 2844728
Kandungan disediakan oleh Daniel Filan. Semua kandungan podcast termasuk episod, grafik dan perihalan podcast dimuat naik dan disediakan terus oleh Daniel Filan atau rakan kongsi platform podcast mereka. Jika anda percaya seseorang menggunakan karya berhak cipta anda tanpa kebenaran anda, anda boleh mengikuti proses yang digariskan di sini https://ms.player.fm/legal.

Many people in the AI alignment space have heard of AI safety via debate - check out AXRP episode 6 (axrp.net/episode/2021/04/08/episode-6-debate-beth-barnes.html) if you need a primer. But how do we get language models to the stage where they can usefully implement debate? In this episode, I talk to Geoffrey Irving about the role of language models in AI safety, as well as three projects he's done that get us closer to making debate happen: using language models to find flaws in themselves, getting language models to back up claims they make with citations, and figuring out how uncertain language models should be about the quality of various answers.

Topics we discuss, and timestamps:

- 00:00:48 - Status update on AI safety via debate

- 00:10:24 - Language models and AI safety

- 00:19:34 - Red teaming language models with language models

- 00:35:31 - GopherCite

- 00:49:10 - Uncertainty Estimation for Language Reward Models

- 01:00:26 - Following Geoffrey's work, and working with him

The transcript: axrp.net/episode/2022/07/01/episode-16-preparing-for-debate-ai-geoffrey-irving.html

Geoffrey's twitter: twitter.com/geoffreyirving

Research we discuss:

- Red Teaming Language Models With Language Models: arxiv.org/abs/2202.03286

- Teaching Language Models to Support Answers with Verified Quotes, aka GopherCite: arxiv.org/abs/2203.11147

- Uncertainty Estimation for Language Reward Models: arxiv.org/abs/2203.07472

- AI Safety via Debate: arxiv.org/abs/1805.00899

- Writeup: progress on AI safety via debate: lesswrong.com/posts/Br4xDbYu4Frwrb64a/writeup-progress-on-ai-safety-via-debate-1

- Eliciting Latent Knowledge: ai-alignment.com/eliciting-latent-knowledge-f977478608fc

- Training Compute-Optimal Large Language Models, aka Chinchilla: arxiv.org/abs/2203.15556

  continue reading

42 episod

Semua episod

×
 
Loading …

Selamat datang ke Player FM

Player FM mengimbas laman-laman web bagi podcast berkualiti tinggi untuk anda nikmati sekarang. Ia merupakan aplikasi podcast terbaik dan berfungsi untuk Android, iPhone, dan web. Daftar untuk melaraskan langganan merentasi peranti.

 

Panduan Rujukan Pantas

Podcast Teratas