News for hackers. Stuff that matters.
Re:Mercury: Ultra-Fast Language Models Based on Diffusion by flir on Monday July 07, 2025 @10:19AM (#44490641)
Don't want to put words in the parent commenter's mouth, but I think the key word is "unsupervised". Claude doesn't know what it doesn't know, and will keep going round the loop until the tests go green, or until the heat death of the universe.
Re:Mercury: Ultra-Fast Language Models Based on Diffusion by mike_hearn on Monday July 07, 2025 @10:20AM (#44490658)
Yes, but you can just impose timeouts to solve that. If it's unsupervised the only cost is computation.