DiscoverPhilosophical Disquisitions109 - How Can We Align Language Models like GPT with Human Values?
109 - How Can We Align Language Models like GPT with Human Values?

109 - How Can We Align Language Models like GPT with Human Values?

Update: 2023-05-30
Share

Description



In this episode of the podcast I chat to Atoosa Kasirzadeh. Atoosa is an Assistant Professor/Chancellor's fellow at the University of Edinburgh. She is also the Director of Research at the Centre for Technomoral Futures at Edinburgh. We chat about the alignment problem in AI development, roughly: how do we ensure that AI acts in a way that is consistent with human values. We focus, in particular, on the alignment problem for language models such as ChatGPT, Bard and Claude, and how some old ideas from the philosophy of language could help us to address this problem.



You can download the episode here or listen below. You can also subscribe the podcast on AppleSpotifyGoogleAmazon or whatever your preferred service might be.



<iframe allowfullscreen="" frameborder="0" height="60" mozallowfullscreen="true" src="https://archive.org/embed/Atoosa" webkitallowfullscreen="true" width="500"></iframe>

Relevant Links





<style type="text/css">
#mc_embed_signup{background:#fff; clear:left; font:14px Helvetica,Arial,sans-serif; }
/* Add your own MailChimp form style overrides in your site stylesheet or in this style block.
We recommend moving this block and the preceding CSS link to the HEAD of your HTML file. */
</style>

<form action="//blogspot.us14.list-manage.com/subscribe/post?u=58eb058b33241976ce21bc706&id=5cb9ef6d67" class="validate" id="mc-embedded-subscribe-form" method="post" name="mc-embedded-subscribe-form" novalidate="" target="_blank">

<label>Subscribe to the newsletter</label>
<input class="email" id="mce-EMAIL" name="EMAIL" required="" type="email" value="" />

<input name="b_58eb058b33241976ce21bc706_5cb9ef6d67" tabindex="-1" type="text" value="" />

<input class="button" id="mc-embedded-subscribe" name="subscribe" type="submit" value="Subscribe" />


</form>


Comments 
loading
00:00
00:00
1.0x

0.5x

0.8x

1.0x

1.25x

1.5x

2.0x

3.0x

Sleep Timer

Off

End of Episode

5 Minutes

10 Minutes

15 Minutes

30 Minutes

45 Minutes

60 Minutes

120 Minutes

109 - How Can We Align Language Models like GPT with Human Values?

109 - How Can We Align Language Models like GPT with Human Values?

John Danaher