Artwork

コンテンツは Daniel Filan によって提供されます。エピソード、グラフィック、ポッドキャストの説明を含むすべてのポッドキャスト コンテンツは、Daniel Filan またはそのポッドキャスト プラットフォーム パートナーによって直接アップロードされ、提供されます。誰かがあなたの著作物をあなたの許可なく使用していると思われる場合は、ここで概説されているプロセスに従うことができますhttps://ja.player.fm/legal
Player FM -ポッドキャストアプリ
Player FMアプリでオフラインにしPlayer FMう!

27 - AI Control with Buck Shlegeris and Ryan Greenblatt

2:56:05
 
シェア
 

Manage episode 412018547 series 2844728
コンテンツは Daniel Filan によって提供されます。エピソード、グラフィック、ポッドキャストの説明を含むすべてのポッドキャスト コンテンツは、Daniel Filan またはそのポッドキャスト プラットフォーム パートナーによって直接アップロードされ、提供されます。誰かがあなたの著作物をあなたの許可なく使用していると思われる場合は、ここで概説されているプロセスに従うことができますhttps://ja.player.fm/legal

A lot of work to prevent AI existential risk takes the form of ensuring that AIs don't want to cause harm or take over the world---or in other words, ensuring that they're aligned. In this episode, I talk with Buck Shlegeris and Ryan Greenblatt about a different approach, called "AI control": ensuring that AI systems couldn't take over the world, even if they were trying to.

Patreon: patreon.com/axrpodcast

Ko-fi: ko-fi.com/axrpodcast

Topics we discuss, and timestamps:

0:00:31 - What is AI control?

0:16:16 - Protocols for AI control

0:22:43 - Which AIs are controllable?

0:29:56 - Preventing dangerous coded AI communication

0:40:42 - Unpredictably uncontrollable AI

0:58:01 - What control looks like

1:08:45 - Is AI control evil?

1:24:42 - Can red teams match misaligned AI?

1:36:51 - How expensive is AI monitoring?

1:52:32 - AI control experiments

2:03:50 - GPT-4's aptitude at inserting backdoors

2:14:50 - How AI control relates to the AI safety field

2:39:25 - How AI control relates to previous Redwood Research work

2:49:16 - How people can work on AI control

2:54:07 - Following Buck and Ryan's research

The transcript: axrp.net/episode/2024/04/11/episode-27-ai-control-buck-shlegeris-ryan-greenblatt.html

Links for Buck and Ryan:

- Buck's twitter/X account: twitter.com/bshlgrs

- Ryan on LessWrong: lesswrong.com/users/ryan_greenblatt

- You can contact both Buck and Ryan by electronic mail at [firstname] [at-sign] rdwrs.com

Main research works we talk about:

- The case for ensuring that powerful AIs are controlled: lesswrong.com/posts/kcKrE9mzEHrdqtDpE/the-case-for-ensuring-that-powerful-ais-are-controlled

- AI Control: Improving Safety Despite Intentional Subversion: arxiv.org/abs/2312.06942

Other things we mention:

- The prototypical catastrophic AI action is getting root access to its datacenter (aka "Hacking the SSH server"): lesswrong.com/posts/BAzCGCys4BkzGDCWR/the-prototypical-catastrophic-ai-action-is-getting-root

- Preventing language models from hiding their reasoning: arxiv.org/abs/2310.18512

- Improving the Welfare of AIs: A Nearcasted Proposal: lesswrong.com/posts/F6HSHzKezkh6aoTr2/improving-the-welfare-of-ais-a-nearcasted-proposal

- Measuring coding challenge competence with APPS: arxiv.org/abs/2105.09938

- Causal Scrubbing: a method for rigorously testing interpretability hypotheses lesswrong.com/posts/JvZhhzycHu2Yd57RN/causal-scrubbing-a-method-for-rigorously-testing

Episode art by Hamish Doodles: hamishdoodles.com

  continue reading

36 つのエピソード

Artwork
iconシェア
 
Manage episode 412018547 series 2844728
コンテンツは Daniel Filan によって提供されます。エピソード、グラフィック、ポッドキャストの説明を含むすべてのポッドキャスト コンテンツは、Daniel Filan またはそのポッドキャスト プラットフォーム パートナーによって直接アップロードされ、提供されます。誰かがあなたの著作物をあなたの許可なく使用していると思われる場合は、ここで概説されているプロセスに従うことができますhttps://ja.player.fm/legal

A lot of work to prevent AI existential risk takes the form of ensuring that AIs don't want to cause harm or take over the world---or in other words, ensuring that they're aligned. In this episode, I talk with Buck Shlegeris and Ryan Greenblatt about a different approach, called "AI control": ensuring that AI systems couldn't take over the world, even if they were trying to.

Patreon: patreon.com/axrpodcast

Ko-fi: ko-fi.com/axrpodcast

Topics we discuss, and timestamps:

0:00:31 - What is AI control?

0:16:16 - Protocols for AI control

0:22:43 - Which AIs are controllable?

0:29:56 - Preventing dangerous coded AI communication

0:40:42 - Unpredictably uncontrollable AI

0:58:01 - What control looks like

1:08:45 - Is AI control evil?

1:24:42 - Can red teams match misaligned AI?

1:36:51 - How expensive is AI monitoring?

1:52:32 - AI control experiments

2:03:50 - GPT-4's aptitude at inserting backdoors

2:14:50 - How AI control relates to the AI safety field

2:39:25 - How AI control relates to previous Redwood Research work

2:49:16 - How people can work on AI control

2:54:07 - Following Buck and Ryan's research

The transcript: axrp.net/episode/2024/04/11/episode-27-ai-control-buck-shlegeris-ryan-greenblatt.html

Links for Buck and Ryan:

- Buck's twitter/X account: twitter.com/bshlgrs

- Ryan on LessWrong: lesswrong.com/users/ryan_greenblatt

- You can contact both Buck and Ryan by electronic mail at [firstname] [at-sign] rdwrs.com

Main research works we talk about:

- The case for ensuring that powerful AIs are controlled: lesswrong.com/posts/kcKrE9mzEHrdqtDpE/the-case-for-ensuring-that-powerful-ais-are-controlled

- AI Control: Improving Safety Despite Intentional Subversion: arxiv.org/abs/2312.06942

Other things we mention:

- The prototypical catastrophic AI action is getting root access to its datacenter (aka "Hacking the SSH server"): lesswrong.com/posts/BAzCGCys4BkzGDCWR/the-prototypical-catastrophic-ai-action-is-getting-root

- Preventing language models from hiding their reasoning: arxiv.org/abs/2310.18512

- Improving the Welfare of AIs: A Nearcasted Proposal: lesswrong.com/posts/F6HSHzKezkh6aoTr2/improving-the-welfare-of-ais-a-nearcasted-proposal

- Measuring coding challenge competence with APPS: arxiv.org/abs/2105.09938

- Causal Scrubbing: a method for rigorously testing interpretability hypotheses lesswrong.com/posts/JvZhhzycHu2Yd57RN/causal-scrubbing-a-method-for-rigorously-testing

Episode art by Hamish Doodles: hamishdoodles.com

  continue reading

36 つのエピソード

すべてのエピソード

×
 
Loading …

プレーヤーFMへようこそ!

Player FMは今からすぐに楽しめるために高品質のポッドキャストをウェブでスキャンしています。 これは最高のポッドキャストアプリで、Android、iPhone、そしてWebで動作します。 全ての端末で購読を同期するためにサインアップしてください。

 

クイックリファレンスガイド