Artificial intelligence is awesome — but should we fear it? How can we stay in charge? Sam Bowman joins Vasant Dhar in episode 58 of Brave New World to discuss the Control Problem — and more.
Also check out:
1. Sam Bowman at NYU Courant, LinkedIn,Twitter and
2. Measuring Progress on Scalable Oversight for Large Language Models — Samuel R Bowman et al.
3. Herbert Simon, Harry Pople and Norbert Wiener.
4. Language Models as Agent Models — Jacob Andreas.
5. The Alignment Problem: Machine Learning and Human Values — Brian Christian.
6. Human Compatible — Stuart Russell.
7. Thinking, Fast and Slow — Daniel Kahneman.
8. ImageNet Classification with Deep Convolutional Neural Networks –Alex Krizhevsky et al.
1. Sam Bowman at NYU Courant, LinkedIn,Twitter and
2. Measuring Progress on Scalable Oversight for Large Language Models — Samuel R Bowman et al.
3. Herbert Simon, Harry Pople and Norbert Wiener.
4. Language Models as Agent Models — Jacob Andreas.
5. The Alignment Problem: Machine Learning and Human Values — Brian Christian.
6. Human Compatible — Stuart Russell.
7. Thinking, Fast and Slow — Daniel Kahneman.
8. ImageNet Classification with Deep Convolutional Neural Networks –Alex Krizhevsky et al.
Check out Vasant Dhar’s newsletter on Substack. Subscription is free!