Pith. sign in

REVIEW 2 cited by

Multi-line AI-assisted Code Authoring

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.04141 v1 pith:Z2AZQRN7 submitted 2024-02-06 cs.SE cs.AI

classification cs.SEcs.AI
keywords suggestionsmulti-linecodeengineersai-assistedauthoringcodecomposedevelopers
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

CodeCompose is an AI-assisted code authoring tool powered by large language models (LLMs) that provides inline suggestions to 10's of thousands of developers at Meta. In this paper, we present how we scaled the product from displaying single-line suggestions to multi-line suggestions. This evolution required us to overcome several unique challenges in improving the usability of these suggestions for developers. First, we discuss how multi-line suggestions can have a 'jarring' effect, as the LLM's suggestions constantly move around the developer's existing code, which would otherwise result in decreased productivity and satisfaction. Second, multi-line suggestions take significantly longer to generate; hence we present several innovative investments we made to reduce the perceived latency for users. These model-hosting optimizations sped up multi-line suggestion latency by 2.5x. Finally, we conduct experiments on 10's of thousands of engineers to understand how multi-line suggestions impact the user experience and contrast this with single-line suggestions. Our experiments reveal that (i) multi-line suggestions account for 42% of total characters accepted (despite only accounting for 16% for displayed suggestions) (ii) multi-line suggestions almost doubled the percentage of keystrokes saved for users from 9% to 17%. Multi-line CodeCompose has been rolled out to all engineers at Meta, and less than 1% of engineers have opted out of multi-line suggestions.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. A Comprehensive Survey of Deep Research: Systems, Methodologies, and Applications

    cs.AI 2025-06 conditional novelty 4.0 of 10

    A survey of 80+ Deep Research systems that proposes a four-layer taxonomy (foundation models, tool use, planning, synthesis) and compares commercial and open-source implementations.

  2. Culturally-Grounded Chain-of-Thought (CG-CoT):Enhancing LLM Performance on Culturally-Specific Tasks in Low-Resource Languages

    cs.CL 2025-06 reject novelty 4.0 of 10

    CG-CoT combines RAG and chain-of-thought prompting for Yoruba proverbs and reports higher cultural depth, but its accuracy result trails a baseline and no human evaluation supports the headline.

Pith tools