Patrick0d — LessWrong

Patrick0d's Shortform

Competitive AI Safety is the loss function to make sure AI goes well

TLDR: * AI safety needs a loss function and Competitive AI safety can deliver it. * The development of AI safety research and tooling is currently diffuse. Lots of researchers, lots of models, lots of techniques. Lots of work that doesn't compound. In the past, diffuse work across an industry...

Jul 166

The AI Safety Puzzle Everyone Avoids: How To Measure Impact, Not Intent.

- Using Landed Writes We do not know the algorithm that transformers follow to compute an answer. This was the original goal with artificial intelligence - we can't easily improve the human brain, so we will build a computer that can think like a human. Then it can learn instantly,...

Jul 22, 20256