✳flâneur — a map of the web's best reading

Nova DasSarma on why information security may be critical to the safe development of AI systems | 80,000 Hours

80000hours.org · 36,617 words · saved by 1 readers

This is a really tough topic in security, because the more you’re trying to defend against, the less usability you have within your system — the less you’re able to do things like iterate fast, collaborate with other people, that sort of thing. There has to be some measure of trust in the system to do any of these things. “The most secure system is the one that you never turn on,” is something we like to say. — Nova DasSarma If a business has spent $100 million developing a product, it’s a fair bet that they don’t want it stolen in two seconds and uploaded to the web where anyone can use it for free. This problem exists in extreme form for AI companies. These days, the electricity and equipment required to train cutting-edge machine learning models that generate uncanny human text and images can cost tens or hundreds of millions of dollars. But once trained, such models may be only a few gigabytes in size and run just fine on ordinary laptops. Today’s guest, the computer scientist and

Nova DasSarma on why information security may be critical to the safe development of AI systems | 80,000 Hours Search for: On this page: Introduction 1 Highlights 2 Articles, books, and other media discussed in the show 3 Transcript 3.1 Rob's intro [00:00:00] 3.2 The interview begins [00:01:08] 3.3 Why computer security matters for AI safety [00:06:03] 3.4 State of the art in information security [00:15:45] 3.5 The hack of Nvidia [00:25:14] 3.6 The most secure systems that exist [00:34:51] 3.7 Formal verification [00:46:26] 3.8 How organisations can protect against hacks [00:52:42] 3.9 Is ML m

Explore this link on the map →

related reading