Boolformer: Symbolic Regression of Logic Functions with Transformers — mentioned by famouswaffles

Sat, 18 Nov 2023 17:46:13 GMT

>ChatGPT has a model of all the text information on the internet, but it remains to be seen what the hard limits of this model are. Before training is complete and loss is maxed, there will be limits on what the "learned so far" model can do that say absolutely nothing about the limits of a perfect(or very close to it) model. It really looks like anything will converge with enough compute. I don't think architecture is particularly important except as "how much compute will this one take?" question. https://nonint.com/2023/06/10/the-it-in-ai-models-is-the-dat... >Does this model let it do…

Paper and discussion history. A mention is not an endorsement.

Boolformer: Symbolic Regression of Logic Functions with Transformers — HN submission

Mon, 02 Oct 2023 20:02:41 GMT

Boolformer: Symbolic Regression of Logic Functions with Transformers

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Boolformer: Symbolic Regression of Logic Functions with Transformers · HackerPapers discussions

Boolformer: Symbolic Regression of Logic Functions with Transformers — mentioned by famouswaffles

Boolformer: Symbolic Regression of Logic Functions with Transformers — HN submission