AI-assisted Code Authoring at Scale: Fine-tuning, deploying, and mixed methods evaluation · HackerPapers discussions

AI-assisted Code Authoring at Scale: Fine-tuning, deploying, and mixed methods evaluation — mentioned by muglug

Mon, 13 May 2024 01:17:20 GMT

GitHub touts a 55% improvement in coding speed based on a study conducted in-house that tested the participants’ ability to paste a pre-written prompt and then check the output: https://github.blog/2022-09-07-research-quantifying-github-c... The effectiveness of a Copilot-like tool trialed at FB showed that 8% of code contributed by participants was sourced from suggestions, but the latter study made no promise about coding velocity: https://arxiv.org/abs/2305.12050. In my own experience the time taken to review machine-generated suggestions often eats into developer time. This is not a…

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

AI-assisted Code Authoring at Scale: Fine-tuning, deploying, and mixed methods evaluation — mentioned by gtani

Tue, 06 Jun 2023 19:34:13 GMT

similar at Meta/facebook https://arxiv.org/abs/2305.12050

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

AI-assisted Code Authoring at Scale: Fine-tuning, deploying, and mixed methods evaluation — HN submission

Sat, 03 Jun 2023 13:38:17 GMT

CodeCompose: A large-scale industrial deployment of AI-assisted code authoring

165 points; 70 discussion replies on HN. Paper and source history. A submission is not an endorsement.