H OW I L EARNED TO S TOP WORRYING A ND LOVE A I-ASSISTED C ODING TOOLS Pe ty o D imitr o v 30th September 2023
Slide 2
About me • 16 years in Software Engineering • Senior Software Architect for Musala Soft / Qinshift • PhD in Computer Science from Technical University Sofia • Lector of course Distributed Systems in Technical University Sofia
Slide 3
Agenda • Initial interest • Reviewed AI-assisted tools • How I use Copilot(X)? • How I use ChatGPT? • How Musala uses AI-assisted tools? • Recent developments • Q&A
How we are introducing it in Musala 1. 2. 3. 4. 5. 6. 7. 8.
Research & pick most promising candidate tools Define questionnaire to assess results Run 1-month trial & collect feedback Research protection mechanisms Identify suitable projects Prepare a list of recommended prompts Require a disclaimer in PR when AI is used Conduct demonstrations and talks to encourage adoption
Weaker features of Copilot • Inline fixing • Code translation • Refactoring
Slide 16
How I use ChatGPT?
Slide 17
For inspiration
Slide 18
As a Rubber ducky
Slide 19
Writing code in “second” languages
Slide 20
Analyze REST APIs (1)
Slide 21
Analyze REST APIs (2)
Slide 22
Analyze REST APIs (3)
Slide 23
Advanced Data Analysis (1)
Display the difference between Main and CountryX and CountryY for the different code types. The numerical values are the number of lines of code.
Slide 24
Advanced Data Analysis (2)
Slide 25
Create diagrams
Slide 26
Generating presentations Generate Python code for creating a PowerPoint presentation on the topic “Basic Python syntax and data types”. Fill in the details with your knowledge. I need 7 slides. Run the code and return the resulting presentation.
Slide 27
Generating presentations
Slide 28
Prompt engineering - Examples or reference
Slide 29
Prompt engineering - Adopt a persona & style
Custom Instructions / Roles
Risks - Devs • Verbose interactions • Hallucinations • Overreliance on the machine
Slide 38
Risks - Data • Leaking proprietary data
• Intellectual Property • Siloed solutions by large vendors
Slide 39
Risks - EU AI Act
Banned
High
Limited
Low
Social credit, realtime biometric
Critical, education, law, employment
Chatbots, image processing
Spam filters, computer games
Slide 40
Latest news November – AWS Gen AI November – 365 Copilot AI Assistant September – Minstral September – ChatGPT Voice & Images September – Copilot Chat* August – Enterprise ChatGPT August – Code Llama (Instruct, Python) July – Llama2 July – Claude2 July – ChatGPT Code Interpreter
Slide 41
Conclusion • A new tool at our disposal like Google & StackOverflow • Only as an assistant • Juniors, Mediors and Seniors benefit differently • Copilot’s advantage is seamless IDE integration • ChatGPT helps with a wider variety of tasks • There are risks & challenges ahead