Conversation with Bryce Wiedenbeck

July 14th, 2017
airisk, ea
A few days ago I spoke with Bryce Wiedenbeck, a CS professor at Swarthmore teaching AI, as part of my project of assessing superintelligence risk. Bryce had relatively similar views to Michael: AGI is possible, it could be a serious problem, but we can't productively work on it now.

Before our conversation he looked some at Concrete Problems in AI Safety (pdf) and Deep Reinforcement Learning from Human Preferences (pdf). His view on both was that they were good work from the perspective of advancing ML but very unlikely to be relevant to making AGI safer: the systems that get us to AGI will look very different from the ones we have now.

One reason is that he saw a lot of learning from humans as being mediated by learning utility functions, but he sees utility functions as a very limited model. Economists and others use utility functions when talking about people because that's mathematically tractable, but it's a bad description of how humans actually behave. Trying to come up with utility functions that best explain human preferences or behavior probably solves some problems nicely and is helpful, but while Bryce wouldn't completely rule it out he thought it was very unlikely to get us to AGI.

We tried to get more into why he thinks implementations for AGI will look vastly different from what we will have today, and couldn't make progress there. Bryce thinks there are deep questions about what intelligence really is that we don't understand yet, and that as we make progress on those questions we'll develop very different sorts of ML systems. If something like today's deep learning is still a part of what we eventually end up with, it's more likely to be something that solves specific problems than as a critical component.

(This has been a common theme in my discussions with people recently: very different intuitions on the distance to AGI in terms of technical work required, and also on whether work we're doing today is likely to transfer.)

Referenced in:

Comment via: google plus, facebook, substack

Recent posts on blogs I like:

Ozy and Vasili Review Lilo and Stitch

Sometimes my seven-year-old, Vasili, wants to see some godawful movie that makes me want to melt my eyeballs out of my head.

via Thing of Things June 27, 2025

Elixir's Last Dance

On May 18th, the contra dance band Elixir had their last gig ever. The dance was packed: there were three hundred people. It was the only dance BIDA has ever done where they sold tickets. People flew from across the country just to hear Elixir play one la…

via Lily Wise's Blog Posts June 5, 2025

Workshop House case study

Lauren Hoffman interviewed me about Workshop House and wrote this post about a community I’m working on building in DC.

via Home April 30, 2025

more     (via openring)