Audio is streamed directly from the publisher (dl.type3.audio) as published in their RSS feed. Play Podcasts does not host this file. Rights-holders can request removal through the copyright & takedown page.
Show Notes
<p> Plus, Detecting Misbehavior in Reasoning Models.</p> <p> In this newsletter, we cover AI companies’ responses to the federal government's request for information on the development of an AI Action Plan. We also discuss an OpenAI paper on detecting misbehavior in reasoning models by monitoring their chains of thought.</p><p> Listen to the AI Safety Newsletter for free on Spotify or Apple Podcasts.</p><p> On January 23, President Trump signed an executive order giving his administration 180 days to develop an “AI Action Plan” to “enhance America's global AI dominance in order to promote human flourishing, economic competitiveness, and national security.”</p><p> Despite the rhetoric of the order, the Trump administration has yet to articulate many policy positions with respect to AI development and safety. In a recent interview, Ben Buchanan—Biden's AI advisor—interpreted the executive order as giving the administration time to develop its AI policies. The AI Action Plan will therefore likely [...]</p> <p>---</p>
<p><b>First published:</b><br/>
March 31st, 2025 </p>
<p><b>Source:</b><br/>
<a href="https://newsletter.safe.ai/p/ai-safety-newsletter-50-ai-action?utm_source=TYPE_III_AUDIO&utm_medium=Podcast&utm_content=Source+URL+in+episode+description&utm_campaign=ai_narration" rel="noopener noreferrer" target="_blank">https://newsletter.safe.ai/p/ai-safety-newsletter-50-ai-action</a> </p>
<p>---</p>
<p>Want more? Check out our <a href="https://newsletter.mlsafety.org/?utm_source=TYPE_III_AUDIO&utm_medium=Podcast&utm_content=Episode+description+footer" target="_blank" rel="noreferrer">ML Safety Newsletter</a> for technical safety research.</p>
<p>Narrated by <a href="https://type3.audio/?utm_source=TYPE_III_AUDIO&utm_medium=Podcast&utm_content=Narrated+by+TYPE+III+AUDIO&utm_term=center_for_ai_safety&utm_campaign=ai_narration" rel="noopener noreferrer" target="_blank">TYPE III AUDIO</a>.</p>
<p>---</p><div style="max-width: 100%";><p><strong>Images from the article:</strong></p><a href="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2fcfe4f8-9b5c-4ce4-9611-683a441c230b_1600x956.png" target="_blank"><img src="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2fcfe4f8-9b5c-4ce4-9611-683a441c230b_1600x956.png" alt="Chat conversation showing discussion about software testing and code implementation strategies.
The green and red messages discuss analyzing polynomial functions and verifying test results." style="max-width: 100%;" /></a><hr style="margin-top: 24px; margin-bottom: 24px;" /><a href="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6544cd82-9ba4-472a-8183-d108be2c86ac_1537x675.png" target="_blank"><img src="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6544cd82-9ba4-472a-8183-d108be2c86ac_1537x675.png" alt="Three graphs comparing baseline and CoT pressure training data over training epochs, showing different cheating scenarios.
The left graph shows no cheating, the middle shows detected cheating, and the right shows undetected cheating attempts during agent training." style="max-width: 100%;" /></a><p><em>Apple Podcasts and Spotify do not show images in the episode description. Try <a href="https://pocketcasts.com/" target="_blank" rel="noreferrer">Pocket Casts</a>, or another podcast app.</em></p></div>