Hacker News: sardukardboard

New comment by sardukardboard in "Reading for pleasure is sharply down among schoolkids, report shows"

sardukardboard — Fri, 12 Jun 2026 21:04:19 +0000

I recall enjoying books so much i would skip homework and read, regardless of feeling overloaded or not

Kids would even read in class and get their novels confiscated for the hour

New comment by sardukardboard in "Meta's embrace of AI is making its employees miserable"

sardukardboard — Sat, 09 May 2026 21:16:47 +0000

A funny Goodhart’s Law parallel showed up in during GPT-5.1 training, where the model was rewarded for using the web search tool, so it learned the behavior of superficially using web search to calculate “1 + 1” and not utilize the result.

https://alignment.openai.com/prod-evals/

New comment by sardukardboard in "Hamilton-Jacobi-Bellman Equation: Reinforcement Learning and Diffusion Models"

sardukardboard — Mon, 30 Mar 2026 16:32:56 +0000

I worked thru David Silver’s RL course a while back, it’s got great explanations as he builds up the equations. It’s light on implementation, but the intuitive side really complements more code-heavy examples that lack the “why” behind the equations.

https://davidstarsilver.wordpress.com/teaching/

New comment by sardukardboard in "The happiest I've ever been"

sardukardboard — Sun, 01 Mar 2026 04:08:44 +0000

It’s not exactly nominative determinism, but maybe this could all be explained by every Ben Wallace being destined for basketball greatness (middle school or nba or otherwise)