![Steve Omohundro on Provably Safe AGI image](https://media.zencastr.com/cdn-cgi/image/width=640,quality=85/image-files/5f32fb7e553efb0248cf8fba/d4ec00f0-c5e6-4eb5-b37a-508e570e9980.jpg)
Future of Life Institute Podcast
Steve Omohundro on Provably Safe AGI
58 Plays
8 months agoSteve Omohundro joins the podcast to discuss Provably Safe Systems, a paper he co-authored with FLI President Max Tegmark. You can read the paper here: https://arxiv.org/pdf/2309.01933.pdf
Timestamps:
00:00 Provably safe AI systems
12:17 Alignment and evaluations
21:08 Proofs about language model behavior
27:11 Can we formalize safety?
30:29 Provable contracts
43:13 Digital replicas of actual systems
46:32 Proof-carrying code
56:25 Can language models think logically?
1:00:44 Can AI do proofs for us?
1:09:23 Hard to proof, easy to verify
1:14:31 Digital neuroscience
1:20:01 Risks of totalitarianism
1:22:29 Can we guarantee safety?
1:25:04 Real-world provable safety
1:29:29 Tamper-proof hardware
1:35:35 Mortal and throttled AI
1:39:23 Least-privilege guarantee
1:41:53 Basic AI drives
1:47:47 AI agency and world models
1:52:08 Self-improving AI
1:58:21 Is AI overhyped now?
Recommended
![Christian Ruhl on Preventing World War III, US-China Hotlines, and Ultraviolet Germicidal Light image](https://media.zencastr.com/cdn-cgi/image/width=90,quality=85/image-files/5f32fb7e553efb0248cf8fba/f0131199-a38a-444a-a9ed-ac9392d415c5.jpg)
4k
![Christian Nunes on Deepfakes (with Max Tegmark) image](https://media.zencastr.com/cdn-cgi/image/width=90,quality=85/image-files/5f32fb7e553efb0248cf8fba/3071bfa4-b30a-4a02-bd78-fd0e22ffc727.png)
3.9k
![Annie Jacobsen on Nuclear War - a Second by Second Timeline image](https://media.zencastr.com/cdn-cgi/image/width=90,quality=85/image-files/5f32fb7e553efb0248cf8fba/cfab3345-b526-4c3d-b455-7e4de6f8558f.jpg)
425
![Katja Grace on the Largest Survey of AI Researchers image](https://media.zencastr.com/cdn-cgi/image/width=90,quality=85/image-files/5f32fb7e553efb0248cf8fba/aacd5d6e-a3b7-4b20-ae08-316dcee1cf0d.jpg)
198
![Holly Elmore on Pausing AI, Hardware Overhang, Safety Research, and Protesting image](https://media.zencastr.com/cdn-cgi/image/width=90,quality=85/image-files/5f32fb7e553efb0248cf8fba/99f22fdb-e0f9-4b90-aa17-e2611b04deba.jpg)
153
![Roman Yampolskiy on Shoggoth, Scaling Laws, and Evidence for AI being Uncontrollable image](https://media.zencastr.com/cdn-cgi/image/width=90,quality=85/image-files/5f32fb7e553efb0248cf8fba/607abe99-5963-4c50-9f35-9b2f6df93679.jpg)
201
![Special: Flo Crivello on AI as a New Form of Life image](https://media.zencastr.com/cdn-cgi/image/width=90,quality=85/image-files/5f32fb7e553efb0248cf8fba/7e23cb89-5319-4372-abca-e55ba9fe54c1.jpg)
93
![Darren McKee on Uncontrollable Superintelligence image](https://media.zencastr.com/cdn-cgi/image/width=90,quality=85/image-files/5f32fb7e553efb0248cf8fba/99ddd4ff-0437-46ea-9721-531260525d9d.jpg)
84
![Mark Brakel on the UK AI Summit and the Future of AI Policy image](https://media.zencastr.com/cdn-cgi/image/width=90,quality=85/image-files/5f32fb7e553efb0248cf8fba/5e72e5de-616d-4dd0-846a-029ac4f726ae.jpg)
75
![Samuel Hammond on AGI and Institutional Disruption image](https://media.zencastr.com/cdn-cgi/image/width=90,quality=85/image-files/5f32fb7e553efb0248cf8fba/696574df-a444-4ab9-a786-69450472343c.jpg)
93
![Imagine A World: What if AI advisors helped us make better decisions? image](https://media.zencastr.com/cdn-cgi/image/width=90,quality=85/image-files/5f32fb7e553efb0248cf8fba/3ab3112b-ee52-44cf-986d-d5e59adcaf3b.jpg)
56
![Imagine A World: What if narrow AI fractured our shared reality? image](https://media.zencastr.com/cdn-cgi/image/width=90,quality=85/image-files/5f32fb7e553efb0248cf8fba/0dfc1044-03c9-4873-b9a3-7cb84cf617a3.jpg)
49
![Imagine A World: What if AI enabled us to communicate with animals? image](https://media.zencastr.com/cdn-cgi/image/width=90,quality=85/image-files/5f32fb7e553efb0248cf8fba/b5352c11-21e1-4aff-8951-e444021e7464.jpg)
58