Productivity Assessment of Neural Code Completion research paper by GitHub, 2022

GitHub · May 13, 2022 · Foundation models 4 years ago

Finds that how often developers accept Copilot's suggestions, more than other usage measures, predicts how productive they feel.

Summarised by hand from the abstract.

More from GitHub

Date	Paper	Topic	Citations
Jun 26, 20233 years ago	Sea Change in Software Development: Economic and Productivity Analysis of the AI-Powered Developer LifecycleAcross nearly a million Copilot users, developers accepted about 30% of suggested code, with the highest acceptance among less experienced developers.Foundation models · Jun 20233 years ago	Foundation models	-
Feb 13, 20233 years ago	The Impact of AI on Developer Productivity: Evidence from GitHub CopilotIn a controlled experiment, developers with GitHub Copilot finished a programming task 55.8% faster than those without it.Foundation models · Feb 20233 years ago	Foundation models	-

Date	Paper	Lab	Citations
Oct 11, 20187 years ago	BERT: Pre-training of Deep Bidirectional Transformers for Language UnderstandingPre-training a Transformer to fill in masked words, then fine-tuning it, beat task-specific models across language understanding tests.Google · Oct 20187 years agoGoogle	Google	121k
May 28, 20206 years ago	Language Models are Few-Shot LearnersGPT-3, a 175B-parameter model, does new tasks from a few examples in the prompt, with no fine-tuning.OpenAI · May 20206 years agoOpenAI	OpenAI	63.7k
Mar 15, 20233 years ago	GPT-4 Technical ReportA multimodal model that passes a simulated bar exam with a score around the top 10% of test takers.OpenAI · Mar 20233 years agoOpenAI	OpenAI	27.3k
Feb 27, 20233 years ago	LLaMA: Open and Efficient Foundation Language ModelsOpen models from 7B to 65B trained only on public data; the 13B model beats GPT-3 on most benchmarks.Meta · Feb 20233 years agoMeta	Meta	21.7k
Jul 31, 20242 years ago	The Llama 3 Herd of ModelsOpen models up to 405B parameters that match leading closed models on many tasks.Meta · Jul 20242 years agoMeta	Meta	18.9k
May 14, 20251 year ago	Qwen3 Technical ReportUnverifiedQwen3, a unified series of large language models, integrates thinking and non-thinking modes, reduces computational resources, and achieves state-of-the-art performance across various tasks and languages.Alibaba (Qwen) · May 2025 · Unverified1 year agoAlibaba (Qwen)	Alibaba (Qwen)	8,100

About this paper

Authors: Albert Ziegler, Eirini Kalliamvakou, Shawn Simister and 5 more
arXiv: 2205.06537 · PDF
Citations: Not counted yet · Semantic Scholar
Upvotes: - · Hugging Face
Lab: GitHub · on Companies · on Paydays · on Releases

Changes

Date	What changed
Sep 26, 2026today	New paperAdded to the listSep 26, 2026today

New papers by email

Monday afternoons, only in weeks with new papers from the labs.