Workflow · saas · workflow
How GitHub Copilot improves contextual understanding with Fill-in-the-Middle and neighboring tabs
Transformer models fast enough to power GitHub Copilot can process only about 6,000 characters at a time, meaning not all of a developer's code can be used as context, and selecting and ordering the right information for the model is the core challenge.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Developer triggers suggestion
GitHub Copilot generates coding suggestions whether the developer is currently writing, has just finished a comment, or is in the middle of code.
Tools used
GitHub CopilotCodexvector databases
Outcome
Neighboring tabs increased user acceptance of suggestions by 5% relative, FIM gave a 10% relative boost in completion acceptance, and research shows developers code up to 55% faster with GitHub Copilot.
What failed first
Prior to Fill-in-the-Middle, only code before the cursor was included in the prompt and the suffix was ignored; the first version also considered only the single file being worked on in the IDE.
Results
Volume5%
Running sinceJune 2021 (technical preview); June 2022 (generally available)
Source
https://github.blog/2023-05-17-how-github-copilot-is-getting-better-at-understanding-your-code/
Grounding & classification
Source type: technical build writeup
19 fields verified against source quotes, 1 dropped as unverifiable.
code generationragcode diff prmetric backedproduction runtime claimedtools describedvendor confirmedsoftwareaccuracy improvementemployee productivitytechnical build writeuprag answering