- Similar to JavaScript β cool/strange/simple at the beginning
- Evolution of tools/practices for defining context/prompts/LLMs
3 months usage of passive use at SCB
- Generating tests
- Explaining code
- Simple refactoring
- Code generation
- Reading errors/extracting values
- Slow generation
- Settings disabled by admin (model, scopes)
Jun 2021: GitHub (Microsoft) released Copilot based on Codex (OpenAI GPT-3)
- Uses FIM (fill-in-the-middle) - new LLM approach for capuring context
- GPT-3.5 Turbo - first success
- Introduced system to block risky patterns/exploits
π https://github.com/settings/copilot
- 
Subscription: - Individual
- Business
- Enterprise (learns codebase, COBOL, scans PRs for the best practices)
 
- 
Models: - GPT-4.0, D3
- Anthropic Claude 3.7
- Gemini 2.0 Flash
 
NLP, ML
- Input Preprocess β prepare for model context and prompt (code related) β processed_prompt
- LM Analysis β neural network analyzes processed_prompt(large body of text)
- Generation β LM generates code/suggestion
- Output Format β indent/highlight
- AMD 2023: Specific HDL Language β generated code better aligned with standards.
- Shopify: Out of 2,000 developers, 75% used Copilot, with 26% accepting suggestions.
- Accenture: Out of 500 developers, 35% accepted suggestions.
- General Satisfaction: 75% of users are satisfied with Copilot.
Competitors:
- Amazon CodeWhisperer
- Cursor VSCode Fork
- Claude Code (recent impressive results)
- Completion β VSCode (ghost text)
- Smart Actions:
- Explain
- Fix
- GenTest
- GenDocs
- Cmd+I β change/refactor
 3.2 Cmd+I in terminal
 3.3 QuickChat
- Commits summary - auto-generated
- PR summary β GitHub interface disabled
- GitHub VSCode_workspaces_workflow β cloud-hosted dev.env
 
- Cmd+Iβ Invoke Copilot
- Cmd+Shift+Iβ Chat window
- Cmd+Alt+Shift+Lβ Open Copilot settings
- Tab/Ctrl+Enterβ Accept suggestion
- Escβ Dismiss suggestion
- Ctrl+Enterβ Show all suggestions
- Alt+][β Next suggestion
- Cmd+/β Add to context
- Short (CONCISE) β LLM chatterbox, order of sentences  sort list|ascendingvs. "can you be so kindβ¦" (can have typos and incomplete)
- Simple (no multi-tasking) β break down complex tasks
- Specific (CONTEXT) β use #tags/@agents
/help
- @workspace
- @vscode
- @terminal
- @directory/@file
- /new - scaffold
- /generate
- /fix
- /tests /doc
- /explain
#file, #editor, #codebase, #sym
- Limited Scope β Check GitHub for the types of projects/languages supported. No latest documentation for openfin/esp.js
- Bias β Can reproduce some bad practices and common errors.
- Security β Potential risk of leaking client data (Copilot takes care of it).
- Public Code β Stochastic machine, can produce public code (license issues, vulnerabilities).
- Inaccurate β Copilot is not a linting tool or compiler (doesnβt fully understand code). Needs human oversight.
- Codex-Only β not a ChatGPT to answer any questions (code/context related)
- Create 3 slides revealJs about Copilot in md format
- As FXO team PM, create a project plan to create FXO tile screen
- // function that generates random prices for 5 major currency pairs
- function generateStock()
- extract common code
- generate tests  right_click
- Q/A comments
// Q: what does rxjs stand for? 
// A: - #terminalLastCommand,- #codebase
- Generator  β Create simple Next.js app
 10@workspace- I want to document how to run this project so that other developers can get started quickly by reading the README.md file
π https://learn.microsoft.com/en-us/training/browse/?terms=github%20copilot


