Papersby GlyphProductivity Assessment of Neural Code Completion research paper by GitHub, 2022
GitHub · Foundation models · May 13, 2022 · 349 citations
What it shows
Finds that how often developers accept Copilot's suggestions, more than other usage measures, predicts how productive they feel.
By Albert Ziegler, Eirini Kalliamvakou, Shawn Simister and 5 more · arXiv 2205.06537 · PDF
Summarised by hand from the abstract.
More from GitHub
All 3Sea 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.
GitHub52 citationsRead →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.GitHub906 citationsRead →
Other foundation models papers
TopicBERT: 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.
Google125k citations33 upvotesRead →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.
OpenAI66.4k citations21 upvotesRead →GPT-4 Technical ReportA multimodal model that passes a simulated bar exam with a score around the top 10% of test takers.OpenAI28.4k citations7 upvotesRead →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.
Meta22.6k citations25 upvotesRead →The Llama 3 Herd of ModelsOpen models up to 405B parameters that match leading closed models on many tasks.Meta20.8k citations119 upvotesRead →Qwen3 Technical ReportQwen3, 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)10.1k citations339 upvotesRead →
About this paper
- Venue
- MAPS@PLDI
- Citations
- 349, 35 influential · Semantic Scholar
- Upvotes
- - · Hugging Face
- Lab
- GitHub · on Companies · on Paydays · on Releases
Changes
Influential citations fell from 36 to 35.
Citations rose from 342 to 349.
Influential citations rose from 32 to 36.
Citations rose from 325 to 342.
Citations rose from 322 to 325.
A first count of 32 influential citations.
A first count of 322 citations.
Added to the list.