Show notes are at https://stevelitchfield.com/sshow/chat.html
…
continue reading
المحتوى المقدم من LessWrong. يتم تحميل جميع محتويات البودكاست بما في ذلك الحلقات والرسومات وأوصاف البودكاست وتقديمها مباشرة بواسطة LessWrong أو شريك منصة البودكاست الخاص بهم. إذا كنت تعتقد أن شخصًا ما يستخدم عملك المحمي بحقوق الطبع والنشر دون إذنك، فيمكنك اتباع العملية الموضحة هنا https://ar.player.fm/legal.
Player FM - تطبيق بودكاست
انتقل إلى وضع عدم الاتصال باستخدام تطبيق Player FM !
انتقل إلى وضع عدم الاتصال باستخدام تطبيق Player FM !
LLMs for Alignment Research: a safety priority?
MP3•منزل الحلقة
Manage episode 412089195 series 3364760
المحتوى المقدم من LessWrong. يتم تحميل جميع محتويات البودكاست بما في ذلك الحلقات والرسومات وأوصاف البودكاست وتقديمها مباشرة بواسطة LessWrong أو شريك منصة البودكاست الخاص بهم. إذا كنت تعتقد أن شخصًا ما يستخدم عملك المحمي بحقوق الطبع والنشر دون إذنك، فيمكنك اتباع العملية الموضحة هنا https://ar.player.fm/legal.
A recent short story by Gabriel Mukobi illustrates a near-term scenario where things go bad because new developments in LLMs allow LLMs to accelerate capabilities research without a correspondingly large acceleration in safety research.
This scenario is disturbingly close to the situation we already find ourselves in. Asking the best LLMs for help with programming vs technical alignment research feels very different (at least to me). LLMs might generate junk code, but you can keep pointing out the problems with the code, and the code will eventually work. This can be faster than doing it myself, in cases where I don't know a language or library well; the LLMs are moderately familiar with everything.
When I try to talk to LLMs about technical AI safety work, however, I just get garbage.
I think a useful safety precaution for frontier AI models would be to make them more useful for [...]
The original text contained 8 footnotes which were omitted from this narration.
---
First published:
April 4th, 2024
Source:
https://www.lesswrong.com/posts/nQwbDPgYvAbqAmAud/llms-for-alignment-research-a-safety-priority
---
Narrated by TYPE III AUDIO.
…
continue reading
This scenario is disturbingly close to the situation we already find ourselves in. Asking the best LLMs for help with programming vs technical alignment research feels very different (at least to me). LLMs might generate junk code, but you can keep pointing out the problems with the code, and the code will eventually work. This can be faster than doing it myself, in cases where I don't know a language or library well; the LLMs are moderately familiar with everything.
When I try to talk to LLMs about technical AI safety work, however, I just get garbage.
I think a useful safety precaution for frontier AI models would be to make them more useful for [...]
The original text contained 8 footnotes which were omitted from this narration.
---
First published:
April 4th, 2024
Source:
https://www.lesswrong.com/posts/nQwbDPgYvAbqAmAud/llms-for-alignment-research-a-safety-priority
---
Narrated by TYPE III AUDIO.
269 حلقات
MP3•منزل الحلقة
Manage episode 412089195 series 3364760
المحتوى المقدم من LessWrong. يتم تحميل جميع محتويات البودكاست بما في ذلك الحلقات والرسومات وأوصاف البودكاست وتقديمها مباشرة بواسطة LessWrong أو شريك منصة البودكاست الخاص بهم. إذا كنت تعتقد أن شخصًا ما يستخدم عملك المحمي بحقوق الطبع والنشر دون إذنك، فيمكنك اتباع العملية الموضحة هنا https://ar.player.fm/legal.
A recent short story by Gabriel Mukobi illustrates a near-term scenario where things go bad because new developments in LLMs allow LLMs to accelerate capabilities research without a correspondingly large acceleration in safety research.
This scenario is disturbingly close to the situation we already find ourselves in. Asking the best LLMs for help with programming vs technical alignment research feels very different (at least to me). LLMs might generate junk code, but you can keep pointing out the problems with the code, and the code will eventually work. This can be faster than doing it myself, in cases where I don't know a language or library well; the LLMs are moderately familiar with everything.
When I try to talk to LLMs about technical AI safety work, however, I just get garbage.
I think a useful safety precaution for frontier AI models would be to make them more useful for [...]
The original text contained 8 footnotes which were omitted from this narration.
---
First published:
April 4th, 2024
Source:
https://www.lesswrong.com/posts/nQwbDPgYvAbqAmAud/llms-for-alignment-research-a-safety-priority
---
Narrated by TYPE III AUDIO.
…
continue reading
This scenario is disturbingly close to the situation we already find ourselves in. Asking the best LLMs for help with programming vs technical alignment research feels very different (at least to me). LLMs might generate junk code, but you can keep pointing out the problems with the code, and the code will eventually work. This can be faster than doing it myself, in cases where I don't know a language or library well; the LLMs are moderately familiar with everything.
When I try to talk to LLMs about technical AI safety work, however, I just get garbage.
I think a useful safety precaution for frontier AI models would be to make them more useful for [...]
The original text contained 8 footnotes which were omitted from this narration.
---
First published:
April 4th, 2024
Source:
https://www.lesswrong.com/posts/nQwbDPgYvAbqAmAud/llms-for-alignment-research-a-safety-priority
---
Narrated by TYPE III AUDIO.
269 حلقات
كل الحلقات
×مرحبًا بك في مشغل أف ام!
يقوم برنامج مشغل أف أم بمسح الويب للحصول على بودكاست عالية الجودة لتستمتع بها الآن. إنه أفضل تطبيق بودكاست ويعمل على أجهزة اندرويد والأيفون والويب. قم بالتسجيل لمزامنة الاشتراكات عبر الأجهزة.