Re:Git Diagramming "The Weave"
by AceJohnny2 on Sunday August 31, 2025 @03:44AM
(#45081236)
> For the presidency, the current benchmark to beat is GPT2 it seems.
You're generous. I would've gone with Eliza, but on second thought that's an insult to Joseph Weizenbaum.
Re:Git Diagramming "The Weave"
by grues-dinner on Sunday August 31, 2025 @06:17AM
(#45082014)
To be representative, the models need a stronger bias towards what the last person they talked to said was the truth rather than what was in their training data.
For example, it could be truly true that a developer is roughly as good as a 1.5b model. It could really be true, in which case we’re not valuing these models for their true simulation power (yet). Might be the best interview test, you must generate hand written code that’s better than a small model (or show better judgement).
For the presidency, the current benchmark to beat is GPT2 it seems.