Hacker News: nelaggy

New comment by nelaggy in "Introducing System One Models and Jev"

nelaggy — Wed, 16 Sep 2026 04:15:59 +0000

insane doom demo i wonder what the limits of its intelligence are? i'm guessing it's not great at reasoning tasks, it seems breaking down the problem helps significantly, but how much does a problem need to be broken down for reliable performance? also this would be huge if it could run locally but it seems like there's no intention to do that at the moment

New comment by nelaggy in "Claude, change the "Add to Cart" button to blue"

nelaggy — Wed, 09 Sep 2026 18:44:50 +0000

delightful user experience 10/10

New comment by nelaggy in "My Mental Model of AI Broke on September 8"

nelaggy — Wed, 09 Sep 2026 18:27:26 +0000

seems to me that many advancements so far are more the product of intelligent effort than pure brilliance, i'm still hopeful that human researchers (and humans in general) will remain better at asking the right questions and making good decisions