Artificial General Intelligence (AGI) Show with Soroush Pour
Claim This Podcastby Soroush Pour
Podcast Overview
<p>When will the world create an artificial intelligence that matches human level capabilities, better known as an artificial general intelligence (AGI)? What will that world look like & how can we ensure it's positive & beneficial for humanity as a whole? Tech entrepreneur & software engineer Soroush Pour (@soroushjp) sits down with AI experts to discuss AGI timelines, pathways, implications, opportunities & risks as we enter this pivotal new era for our planet and species.<br><br>Hosted by Soroush Pour. Follow me for more AGI content:<br>Twitter: <a href="https://twitter.com/soroushjp">https://twitter.com/soroushjp</a><br>LinkedIn: <a href="https://www.linkedin.com/in/soroushjp/">https://www.linkedin.com/in/soroushjp/</a></p>
Language
🇺🇲
Publishing Since
11/12/2022
Reach the team behind Artificial General Intelligence (AGI) Show with Soroush Pour
Verified contact details for this show aren't on file yet — sign up to get notified when they land.
Recent Episodes
June 19, 2024
Ep 14 - Interp, latent robustness, RLHF limitations w/ Stephen Casper (PhD AI researcher, MIT)
<p>We speak with Stephen Casper, or "Cas" as his friends call him. Cas is a PhD student at MIT in the Computer Science (EECS) department, in the Algorithmic Alignment Group advised by Prof Dylan Hadfield-Menell. Formerly, he worked with the Harvard Kreiman Lab and the Center for Human-Compatible AI (CHAI) at Berkeley. His work focuses on better understanding the internal workings of AI models (better known as “interpretability”), making them robust to various kinds of adversarial attacks, and calling out the current technical and policy gaps when it comes to making sure our future with AI goes well. He’s particularly interested in finding automated ways of finding & fixing flaws in how deep neural nets handle human-interpretable concepts.<br/><br/>We talk to Stephen about:<br/><br/>* His technical AI safety work in the areas of:<br/> * Interpretability<br/> * Latent attacks and adversarial robustness<br/> * Model unlearning<br/> * The limitations of RLHF<br/>* Cas' journey to becoming an AI safety researcher<br/>* How he thinks the AI safety field is going and whether we're on track for a positive future with AI<br/>* Where he sees the biggest risks coming with AI<br/>* Gaps in the AI safety field that people should work on<br/>* Advice for early career researchers<br/><br/>Hosted by Soroush Pour. Follow me for more AGI content:<br/>Twitter: https://twitter.com/soroushjp<br/>LinkedIn: https://www.linkedin.com/in/soroushjp/<br/><br/>== Show links ==<br/><br/>-- Follow Stephen --<br/><br/>* Website: https://stephencasper.com/<br/>* Email: (see Cas' website above)<br/>* Twitter: https://twitter.com/StephenLCasper<br/>* Google Scholar: https://scholar.google.com/citations?user=zaF8UJcAAAAJ<br/><br/>-- Further resources --<br/><br/>* Automated jailbreaks / red-teaming paper that Cas and I worked on together (2023) - https://twitter.com/soroushjp/status/1721950722626077067<br/>* Sam Marks paper on Sparse Autoencoders (SAEs) - https://arxiv.org/abs/2403.19647<br/>* Interpretability papers involving downstream tasks - See section 4.2 of https://arxiv.org/abs/2401.14446<br/>* MMET paper on model editing - https://arxiv.org/abs/2210.07229<br/>* Motte & bailey definition - https://en.wikipedia.org/wiki/Motte-and-bailey_fallacy<br/>* Bomb-making papers tweet thread by Cas - https://twitter.com/StephenLCasper/status/1780370601171198246<br/>* Paper: undoing safety with as few as 10 examples - https://arxiv.org/abs/2310.03693<br/>* Recommended papers on latent adversarial training (LAT) -<br/> * https://ai-alignment.com/training-robust-corrigibility-ce0e0a3b9b4d<br/> * https://arxiv.org/abs/2403.05030<br/>* Scoping (related to model unlearning) blog post by Cas - https://www.alignmentforum.org/posts/mFAvspg4sXkrfZ7FA/deep-forgetting-and-unlearning-for-safely-scoped-llms<br/>* Defending against failure modes using LAT - https://arxiv.org/abs/2403.05030<br/>* Cas' systems for reading for research -<br/> * Follow ML Twitter<br/> * Use a combination of the following two search tools for new Arxiv papers:<br/> * https://vjunetxuuftofi.github.io/arxivredirect/<br/> * https://chromewebstore.google.com/detail/highlight-this-finds-and/fgmbnmjmbjenlhbefngfibmjkpbcljaj?pli=1<br/> * Skim a new paper or two a day + take brief notes in a searchable notes app<br/>* Recommended people to follow to learn about how to impact the world through research -<br/> * Dan Hendrycks<br/> * Been Kim<br/> * Jacob Steinhardt<br/> * Nicolas Carlini<br/> * Paul Christiano<br/> * Ethan Perez<br/><br/>Recorded May 1, 2024</p>
June 19, 2024
Ep 13 - AI researchers expect AGI sooner w/ Katja Grace (Co-founder & Lead Researcher, AI Impacts)
<p>We speak with Katja Grace. Katja is the co-founder and lead researcher at AI Impacts, a research group trying to answer key questions about the future of AI — when certain capabilities will arise, what will AI look like, how it will all go for humanity.<br/><br/>We talk to Katja about:<br/><br/>* How AI Impacts latest rigorous survey of leading AI researchers shows they've dramatically reduced their timelines to when AI will successfully tackle all human tasks & occupations.<br/>* The survey's methodology and why we can be confident in its results<br/>* Responses to the survey<br/>* Katja's journey into the field of AI forecasting<br/>* Katja's thoughts about the future of AI, given her long tenure studying AI futures and its impacts<br/><br/>Hosted by Soroush Pour. Follow me for more AGI content:<br/>Twitter: https://twitter.com/soroushjp<br/>LinkedIn: https://www.linkedin.com/in/soroushjp/<br/><br/>== Show links ==<br/><br/>-- Follow Katja --<br/><br/>* Website: https://katjagrace.com/<br/>* Twitter: https://x.com/katjagrace<br/><br/>-- Further resources --<br/><br/>* The 2023 survey of AI researchers views: https://wiki.aiimpacts.org/ai_timelines/predictions_of_human-level_ai_timelines/ai_timeline_surveys/2023_expert_survey_on_progress_in_ai<br/>* AI Impacts: https://aiimpacts.org/<br/>* AI Impacts' Substack: https://blog.aiimpacts.org/<br/>* Joe Carlsmith on Power Seeking AI: https://arxiv.org/abs/2206.13353<br/> * Abbreviated version: https://joecarlsmith.com/2023/03/22/existential-risk-from-power-seeking-ai-shorter-version<br/>* Fragile World hypothesis by Nick Bostrom: https://nickbostrom.com/papers/vulnerable.pdf<br/><br/>Recorded Feb 22, 2024</p>
March 8, 2024
Ep 12 - Education & advocacy for AI safety w/ Rob Miles (YouTube host)
<p>We speak with Rob Miles. Rob is the host of the “Robert Miles AI Safety” channel on YouTube, the single most popular AI alignment video series out there — he has 145,000 subscribers and his top video has ~600,000 views. He goes much deeper than many educational resources out there on alignment, going into important technical topics like the orthogonality thesis, inner misalignment, and instrumental convergence.<br/><br/>Through his work, Robert has educated thousands on AI safety, including many now working on advocacy, policy, and technical research. His work has been invaluable for teaching and inspiring the next generation of AI safety experts and deepening public support for the cause.<br/><br/>Prior to his AIS education work, Robert studied Computer Science at the University of Nottingham.<br/><br/>We talk to Rob about:<br/><br/>* What got him into AI safety<br/>* How he started making educational videos for AI safety<br/>* What he's working on now<br/>* His top advice for people who also want to do education & advocacy work, really in any field, but especially for AI safety<br/>* How he thinks AI safety is currently going as a field of work<br/>* What he wishes more people were working on within AI safety<br/><br/>Hosted by Soroush Pour. Follow me for more AGI content:<br/>Twitter: https://twitter.com/soroushjp<br/>LinkedIn: https://www.linkedin.com/in/soroushjp/<br/><br/>== Show links ==<br/><br/>-- About Rob --<br/><br/>* Rob Miles AI Safety channel - https://www.youtube.com/@RobertMilesAI<br/>* Twitter - https://twitter.com/robertskmiles<br/><br/>-- Further resources --<br/><br/>* Channel where Rob first started making videos: https://www.youtube.com/@Computerphile<br/>* Podcast ep w/ Eliezer Yudkowsky, who first convinced Rob to take AI safety seriously through reading Yudkowsky's writings: https://lexfridman.com/eliezer-yudkowsky/<br/><br/>Recording date: Nov 21, 2023</p>
15 total episodes available
Similar Podcasts
Discover related shows you might enjoy
Deep-dive analytics for Artificial General Intelligence (AGI) Show with Soroush Pour
Frequently asked questions
Have a different question and can't find the answer you're looking for? Reach out to our support team by sending us an email and we'll get back to you as soon as we can.
- What is Artificial General Intelligence (AGI) Show with Soroush Pour?
<p>When will the world create an artificial intelligence that matches human level capabilities, better known as an artificial general intelligence (AGI)? What will that world look like & how can we ensure it's positive & beneficial for humanity as a whole? Tech entrepreneur & software engineer Soroush Pour (@soroushjp) sits down with AI experts to discuss AGI timelines, pathways, implications, opportunities & risks as we enter this pivotal new era for our planet and species.<br><br>Hosted by Soroush Pour. Follow me for more AGI content:<br>Twitter: <a href="https://twitter.com/soroushjp">https://twitter.com/soroushjp</a><br>LinkedIn: <a href="https://www.linkedin.com/in/soroushjp/">https://www.linkedin.com/in/soroushjp/</a></p> - How often does this podcast release new episodes?
This podcast updates weekly.
- Where can I listen to this podcast?
This podcast is available on 10 platforms including Apple Podcasts, Spotify, and more. You can also use the RSS feed directly.
- Does this podcast accept guests?
Yes, this podcast regularly features guests.
Legal Disclaimer
Pod Engine is not affiliated with, endorsed by, or officially connected with any of the podcasts displayed on this platform. We operate independently as a podcast discovery and analytics service.
All podcast artwork, thumbnails, and content displayed on this page are the property of their respective owners and are protected by applicable copyright laws. This includes, but is not limited to, podcast cover art, episode artwork, show descriptions, episode titles, transcripts, audio snippets, and any other content originating from the podcast creators or their licensors.
We display this content under fair use principles and/or implied license for the purpose of podcast discovery, information, and commentary. We make no claim of ownership over any podcast content, artwork, or related materials shown on this platform. All trademarks, service marks, and trade names are the property of their respective owners.
While we strive to ensure all content usage is properly authorized, if you are a rights holder and believe your content is being used inappropriately or without proper authorization, please contact us immediately at hey@podengine.ai for prompt review and appropriate action, which may include content removal or proper attribution.
By accessing and using this platform, you acknowledge and agree to respect all applicable copyright laws and intellectual property rights of content owners. Any unauthorized reproduction, distribution, or commercial use of the content displayed on this platform is strictly prohibited.