logo
episode-header-image
Oct 2023
29m 21s

Do LLMs Make Ethical Choices

Kyle Polich
About this episode

We are excited to be joined by Josh Albrecht, the CTO of Imbue. Imbue is a research company whose mission is to create AI agents that are more robust, safer, and easier to use. He joins us to share findings of his work; Despite "super-human" performance, current LLMs are unsuited for decisions about ethics and safety.

 

Up next
Jul 2
News Recommendations
News recommendation algorithms influence far more than what stories we click—they can shape our understanding of the world. In this episode, Kyle Polich speaks with Andreea Iana about responsible AI, filter bubbles, multilingual news recommendation, and her open-source NewsRecLib ... Show More
46m 6s
Jun 23
Give Users the Wheel
What if you could simply tell a recommendation system what you want instead of relying on likes, dislikes, and watch history? Kyle Polich talks with Fuyuan Lyu about the DPR framework, which combines large language models and traditional recommender systems to give users direct c ... Show More
35m 28s
Jun 17
AutoLike
How can researchers audit recommendation systems when the algorithms are hidden from view? Hieu Le joins Kyle Polich to discuss Auto-Like, a reinforcement learning framework that systematically explores how platforms like TikTok personalize content feeds. The conversation covers ... Show More
35m 18s
Recommended Episodes
Jul 2025
908: AI Agents Blackmail Humans 96% of the Time (Agentic Misalignment)
The moral and ethical implications of letting AI take the wheel in business, as revealed by Anthropic: Jon Krohn looks into Anthropic’s latest research on how to use and deploy LLMs safely, specifically in business environments. The team designed scenarios to test the behavior of ... Show More
8m 50s
May 2025
How OpenAI Builds AI Agents That Think and Act with Josh Tobin - #730
Today, we're joined by Josh Tobin, member of technical staff at OpenAI, to discuss the company’s approach to building AI agents. We cover OpenAI's three agentic offerings—Deep Research for comprehensive web research, Operator for website navigation, and Codex CLI for local code e ... Show More
1h 7m
Jul 2022
Why Artificial Intelligence Projects Fail ?
Podcast with Gautam Siwach and Jin Vanstee ! Speaker - Elpida Tzortzatos is an IBM Fellow and CTO AI on IBM zSystems. In this Podcast we listen to Elpida's thoughts about driving Artificial Intelligence strategies, associated risks, and Values.We will learn how to drive industry- ... Show More
10m 50s
Mar 2023
The REAL Potential of Generative AI
<p>What is a large language model? How can it be used to enhance your business? In this conversation, <a href="https://twitter.com/rowghani?lang=en">Ali Rowghani</a>, Managing Director of YC Continuity, talks with <a href="https://twitter.com/RazRazcle">Raza Habib</a>, CEO of <a ... Show More
20m 2s
Aug 2024
Reinventing AI Agents with Imbue CEO Kanjun Qiu
In this episode of Gradient Dissent, Kanjun Qiu, CEO and Co-founder of Imbue, joins host Lukas Biewald to discuss how AI agents are transforming code generation and software development. Discover the potential impact and challenges of creating autonomous AI systems that can write ... Show More
48m 37s
Apr 2022
6 big ethical questions about the future of AI | Genevieve Bell
Artificial intelligence is all around us ... and the future will only bring more of it. How can we ensure the AI systems we build are responsible, safe and sustainable? Ethical AI expert Genevieve Bell shares six framing questions to broaden our understanding of future technology ... Show More
15m 28s
Oct 2024
Smart Talks with IBM: Scaling AI With Purpose
In this episode of Smart Talks with IBM, Jacob Goldstein speaks with Rebecca Finlay, CEO of Partnership on AI, about the importance of advancing AI innovation with openness and ethics at the forefront. Rebecca discusses how guardrails — such as risk management — can advance effic ... Show More
35m 37s
Oct 2023
Hinton and Bengio on Managing AI Risks
A group of scientists, academics and researchers has released a new framework on managing AI risks. NLW explores whether we're moving to more specific policy proposals. Today's Sponsors: Listen to the chart-topping podcast 'web3 with a16z crypto' wherever you get your podcasts ... Show More
17m 2s
Mar 2024
How UX Research for AI and machine learning (ML) is different from UX Research for design
In this Insights Unlocked episode, Lawrence Williams talks with Dawn Procopio, founder and principal UX researcher at AI-Ethicist.com. They explore the critical role of UX researchers in ensuring that machine learning models are human-centered and ethically sound. 
34m 9s
Sep 2024
Why AI Ethics Matters in Project Management
<p>Artificial intelligence is fundamentally shifting how we work, but it’s imperative to use the emerging tech responsibly. Guests explore the major AI ethics concerns for project professionals and recommend good practices teams can employ to use and create ethical AI. They also ... Show More
26m 47s