Tag: opinion

All the articles with the tag "opinion".

• What I'm looking into this year

  Published:Oct 7, 2026 |  at 02:30 AM

  Four questions I'm spending senior year on: world models, optimizers, how to evaluate AI harnesses, and whether a model can know when it's wrong.

• When agents fail because their picture of the world is stale

  Published:Sep 16, 2026 |  at 03:05 AM

  Stale facts, lost corrections, and unchecked tool results can derail an agent. I'm exploring how explicit state and verification might help.

• Where talking to my computer works better than typing

  Published:Aug 22, 2026 |  at 09:15 PM

  Why I think voice is winning for getting thoughts out of your head, where it still loses to a keyboard, and what voice software is still missing.

• Can a model do math it doesn't understand?

  Published:Jul 9, 2026 |  at 02:50 AM

  Searle's Chinese Room restated for machine-written proofs, what interpretability says models actually do when they add, and why I think 'can it tell when it's wrong' is a better question than 'does it understand'.