Dan James
@attika.bsky.social
Doer of stuff, occasionally build robots
Finding the objectively correct answer to a hyper specific question is miles different.
It also concretely demolishes the naysaying that LLMs “parrot” their answers. It’s borderline impossible for the training data to have had that exact question. It had to perform actual reasoning to get there.
It also concretely demolishes the naysaying that LLMs “parrot” their answers. It’s borderline impossible for the training data to have had that exact question. It had to perform actual reasoning to get there.
January 30, 2025 at 7:11 AM
Finding the objectively correct answer to a hyper specific question is miles different.
It also concretely demolishes the naysaying that LLMs “parrot” their answers. It’s borderline impossible for the training data to have had that exact question. It had to perform actual reasoning to get there.
It also concretely demolishes the naysaying that LLMs “parrot” their answers. It’s borderline impossible for the training data to have had that exact question. It had to perform actual reasoning to get there.
Some of my greatest TOTK moments are realizing I’m too stupid to progress the way the devs intended, then crafting the dumbest contraption I can imagine through pure spite and frustration and then watching the game go “sure, why not”
May 13, 2023 at 4:55 AM
Some of my greatest TOTK moments are realizing I’m too stupid to progress the way the devs intended, then crafting the dumbest contraption I can imagine through pure spite and frustration and then watching the game go “sure, why not”