<div class="separator" style="clear: both; text-align: center;"></div><div class="separator" style="clear: both; text-align: center;"><a href="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgBxAVVFPiQnuDnrGnUUYe8exvwE2v2y-vDkXuSsg1vcOGpewr8_96LuAUvw7DqZBEzGO5klFVCCSlKP3Dmr1pWPfgHZ9NZa3CvuPzW6cwVoz1CJaRaNFDsj0Qtg7yFramYXFh22yVIrrTxwpYvcJOWunXtF0Hx16MbYUQfQKkVKfZWbdtFs6aQnFfn/s300/EDIUNI230217-69.jpg.webp" imageanchor="1" style="margin-left: 1em; margin-right: 1em;"><img border="0" data-original-height="300" data-original-width="248" height="400" src="https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgBxAVVFPiQnuDnrGnUUYe8exvwE2v2y-vDkXuSsg1vcOGpewr8_96LuAUvw7DqZBEzGO5klFVCCSlKP3Dmr1pWPfgHZ9NZa3CvuPzW6cwVoz1CJaRaNFDsj0Qtg7yFramYXFh22yVIrrTxwpYvcJOWunXtF0Hx16MbYUQfQKkVKfZWbdtFs6aQnFfn/w331-h400/EDIUNI230217-69.jpg.webp" width="331" /></a></div><p></p><p>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.</p>

<p>You can download the episode <a href="https://ia902601.us.archive.org/18/items/Atoosa/Atoosa.mp3">here</a> or listen below. You can also subscribe the podcast on&nbsp;<a href="https://podcasts.apple.com/us/podcast/ethics-of-academia/id1629410927">Apple</a>,&nbsp;<a href="https://open.spotify.com/show/6NZhROFYBj8hln3R7Jzcl0">Spotify</a>,&nbsp;<a href="https://podcasts.google.com/feed/aHR0cHM6Ly9ldGhpY3NvZmFjYWRlbWlhLndvcmRwcmVzcy5jb20vY2F0ZWdvcnkvcG9kY2FzdC9mZWVkLw?sa=X&ved=0CAcQrrcFahcKEwiAoMzQ1eH4AhUAAAAAHQAAAAAQDg">Google</a>,&nbsp;<a href="https://music.amazon.com/podcasts/11b039ff-0bf9-47eb-8506-b8feb03b265d/ethics-of-academia?">Amazon</a>&nbsp;or whatever your preferred service might be.</p>

<iframe allowfullscreen="" frameborder="0" height="60" mozallowfullscreen="true" src="https://archive.org/embed/Atoosa" webkitallowfullscreen="true" width="500"></iframe><div></div><h3 style="text-align: left;">Relevant Links</h3><div><ul style="text-align: left;"><li><a href="https://kasirzadeh.org/">Atoosa's webpage</a></li></ul><ul style="text-align: left;"><li>Atoosa's paper (with Iason Gabriel) '<a href="https://link.springer.com/article/10.1007/s13347-023-00606-x">In Conversation with AI: Aligning Language Models with Human Values'</a></li></ul><div></div></div><div><span style="background-color: #b2b2b2;"></span></div><div><span style="background-color: #b2b2b2;"></span>

<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>
<div id="mc_embed_signup">
<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">
    <div id="mc_embed_signup_scroll">
 <label>Subscribe to the newsletter</label>
 <input class="email" id="mce-EMAIL" name="EMAIL" required="" type="email" value="" />
    
    <div aria-hidden="true" style="left: -5000px; position: absolute;"><input name="b_58eb058b33241976ce21bc706_5cb9ef6d67" tabindex="-1" type="text" value="" /></div>
    <div class="clear"><input class="button" id="mc-embedded-subscribe" name="subscribe" type="submit" value="Subscribe" /></div>
    </div>
</form>
</div>

</div>

Podurama

Home

Trending

Personal

Your Podcasts

New Episodes

My Files

Favourite Episodes

Tags (Folders)

Recently Played

Bookmarks

Followed Playlists

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

Philosophical Disquisitions

AI Chapters

AI Insights

Reviews