The AI Revolution in Software Development: From Code Writing to Quality Assurance
summary
Panel reports concrete numbers and working experiments: coding assistants run 10–15 uses per day on some teams with about 37% acceptance of suggestions, Amazon Q and Bedrock, GitHub Copilot and local Llama on Raspberry Pi show tradeoffs, and ChatGPT creates a playable chess CLI in 60 minutes while Google Bard produced broken code; prototypes save hours but require human fixes, prompt engineering and agents get built and evaluated, and local vs cloud models determine context window, compliance and whether solutions actually work.
AI-written summary · about
chapters (10)
- 0:00Welcome
- 1:05Panelists and backgrounds
- 2:53AI tools in development
- 8:31Productivity and code quality
- 15:28Privacy and local AI
- 21:06Trust in AI vs humans
- 27:06Future of development roles
- 33:16Skills in AI-driven development
- 37:53Customizing AI tools
- 43:53Closing thoughts
related talks
30mThe AI Revolution in Coding
01h 16mAI in Software Development: Boosting Efficiency
50mPanel: Beyond The Vibe: Code Quality First
33mAI assisted software delivery
27mAI for software development: A reality check
16mCoding Reinvented How AI Agents Are Shaping the Future of Software Development
01h 02mPANEL - Unleashing the Future: The Impact of Gen AI on Development Productivity
45mPanel Discussion on AI for Code Generation