Understanding GPT tokenizers(simonwillison.net)

380 points by simonw 3 years ago | 110 comments

Simon Willison blog post explaining how GPT tokenizers convert text to integer tokens, with an Observable notebook tool for encoding, decoding and searching tokens.

TabPFN and TabICL vs. tuned XGBoost: the model that doesn't train won 14/14(efraingaray.com)

21 points by EfrainGaray 28 days ago | 9 comments

Blog post benchmarking TabPFN and TabICL foundation models against tuned XGBoost on fourteen tabular datasets, finding the no-training models won all fourteen.

Everything Picolisp can do, and more(picolisp.com)

86 points by damir 1 year ago | 8 comments

Show HN: Kalosm an embeddable framework for pre-trained models in Rust(floneum.com)

53 points by Evan-Almloff 2 years ago | 6 comments

Supertoast tables(hatchet.run)

43 points by abelanger 7 months ago | 6 comments

COBOL for GCC Development(cobolworx.com)

64 points by pantalaimon 2 years ago | 19 comments