Program Synthesis with Large Language Models · HackerPapers discussions

Program Synthesis with Large Language Models — mentioned by moyix

Fri, 11 Feb 2022 19:11:01 GMT

Yeah it's interesting how moving up a level of abstraction works well here! "Write me a function that multiplies two numbers" works much better than trying to get it to multiply the numbers themselves. There's a recent-ish paper exploring this: https://arxiv.org/abs/2108.07732

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

Program Synthesis with Large Language Models — mentioned by muds

Wed, 18 Aug 2021 03:34:40 GMT

Great work! I found the results in Fig 16 pretty interesting [0]... From response 1, it seems that the model has very little confidence in its decision but get the correct answer while, on the contrary, in response 3, the model seems very confident in its incorrect answer. Is this usually a trend that you see with large models? How hard is it, generally, to make such models "aware" of their own shortcomings? [0]: https://arxiv.org/pdf/2108.07732.pdf#figure.caption.21

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

Program Synthesis with Large Language Models — HN submission

Wed, 18 Aug 2021 02:05:07 GMT

Program Synthesis with Large Language Models

63 points; 20 discussion replies on HN. Paper and source history. A submission is not an endorsement.