Get it on Google Play

87. Evan Hubinger - The Inner Alignment Problem

87. Evan Hubinger - The Inner Alignment Problem

Author: The TDS team June 9, 2021 Duration: 1:09:32
Towards Data Science
Technology

How can you know that a super-intelligent AI is trying to do what you asked it to do?

The answer, it turns out, is: not easily. And unfortunately, an increasing number of AI safety researchers are warning that this is a problem we’re going to have to solve sooner rather than later, if we want to avoid bad outcomes — which may include a species-level catastrophe.

The type of failure mode whereby AIs optimize for things other than those we ask them to is known as an inner alignment failure in the context of AI safety. It’s distinct from outer alignment failure, which is what happens when you ask your AI to do something that turns out to be dangerous, and it was only recognized by AI safety researchers as its own category of risk in 2019. And the researcher who led that effort is my guest for this episode of the podcast, Evan Hubinger.

Evan is an AI safety veteran who’s done research at leading AI labs like OpenAI, and whose experience also includes stints at Google, Ripple and Yelp. He currently works at the Machine Intelligence Research Institute (MIRI) as a Research Fellow, and joined me to talk about his views on AI safety, the alignment problem, and whether humanity is likely to survive the advent of superintelligent AI.


While the active production of Towards Data Science has concluded, its archive remains a vital resource. Created by The TDS team, this collection captures a specific moment in the rapid evolution of data science and artificial intelligence. Each conversation pulls you directly into the room with leading researchers and practitioners who were shaping the tools and theories of their time. The discussions are not abstract lectures; they are grounded explorations of real-world problems, ethical dilemmas, and technical challenges that defined the field's trajectory. You'll hear experts dissect the implications of their work, from algorithmic fairness to the practicalities of deploying models at scale. This podcast served as a forum for nuanced debate, where complex ideas were unpacked with clarity and depth. Listening now offers a unique historical perspective, a chance to understand the foundational conversations that continue to influence where technology is headed next. The archive of Towards Data Science stands as a substantive record of insight, preserving the voices and questions from the forefront of a digital revolution.
Author: Language: en-us Episodes: 50

Official website RSS
youtubelinkedinmedium
Towards Data Science
Podcast Episodes
100. Max Jaderberg - Open-ended learning at DeepMind [not-audio_url] [/not-audio_url]

Duration: 45:25
On the face of it, there’s no obvious limit to the reinforcement learning paradigm: you put an agent in an environment and reward it for taking good actions until it masters a task. And by last year, RL had achieved some…
99. Margaret Mitchell - (Practical) AI ethics [not-audio_url] [/not-audio_url]

Duration: 45:43
Bias gets a bad rap in machine learning. And yet, the whole point of a machine learning model is that it biases certain inputs to certain outputs — a picture of a cat to a label that says “cat”, for example. Machine lear…
98. Mike Tung - Are knowledge graphs AI’s next big thing? [not-audio_url] [/not-audio_url]

Duration: 48:56
As impressive as they are, language models like GPT-3 and BERT all have the same problem: they’re trained on reams of internet data to imitate human writing. And human writing is often wrong, biased, or both, which means…
97. Anthony Habayeb - The present and future of AI regulation [not-audio_url] [/not-audio_url]

Duration: 49:31
Corporate governance of AI doesn’t sound like a sexy topic, but it’s rapidly becoming one of the most important challenges for big companies that rely on machine learning models to deliver value for their customers. More…
96. Jan Leike - AI alignment at OpenAI [not-audio_url] [/not-audio_url]

Duration: 1:05:17
The more powerful our AIs become, the more we’ll have to ensure that they’re doing exactly what we want. If we don’t, we risk building AIs that use dangerously creative solutions that have side-effects that could be unde…
95. Francesca Rossi - Thinking, fast and slow: AI edition [not-audio_url] [/not-audio_url]

Duration: 46:42
The recent success of large transformer models in AI raises new questions about the limits of current strategies: can we expect deep learning, reinforcement learning and other prosaic AI techniques to get us all the way…
94. Divya Siddarth - Are we thinking about AI wrong? [not-audio_url] [/not-audio_url]

Duration: 1:02:44
AI research is often framed as a kind of human-versus-machine rivalry that will inevitably lead to the defeat — and even wholesale replacement of — human beings by artificial superintelligences that have their own sense…
92. Daniel Filan - Peering into neural nets for AI safety [not-audio_url] [/not-audio_url]

Duration: 1:06:02
Many AI researchers think it’s going to be hard to design AI systems that continue to remain safe as AI capabilities increase. We’ve seen already on the podcast that the field of AI alignment has emerged to tackle this p…
91. Peter Gao - Self-driving cars: Past, present and future [not-audio_url] [/not-audio_url]

Duration: 1:01:21
Cruise is a self-driving car startup founded in 2013 — at a time when most people thought of self-driving cars as the stuff of science fiction. And yet, just three years later, the company was acquired by GM for over a b…

«12345»