AI, Make It So - A Dive into the Universe of Prompt Engineering
summary
Generative tools like GitHub Copilot and ChatGPT move from autocomplete to running code, plugins and web access, plus a ChatGPT code interpreter that executes Python and produces visual outputs. Examples include automated test-data creation, a no-code vulnerability scanner that surfaces real findings, and text-to-video/image edits that convincingly recompose scenes. Risks include prompt injection, provenance watermarking and PI-masking libraries. The direction shifts engineering from hand-coding features to building the systems that generate and orchestrate agents and prompts.
AI-written summary · about
chapters (17)
- 0:00Introduction
- 1:45Generative AI impact
- 2:49AI-assisted coding tools
- 5:17Prompt engineering as code
- 6:44Security risks in prompt injection
- 8:53Detecting AI content
- 9:58Privacy and data masking
- 11:00AI art optimization
- 13:21Monetizing AI prompts
- 14:24AI video editing
- 15:51Virtual production 3D
- 16:35AI-generated apps without coding
- 17:40AI goal-based agents
- 18:46Browser AI models
- 19:31AI training AI
- 20:16Future of prompt engineering
- 21:22Q&A
related talks
46mAI Integration for Devs: ChatGPT and Copilot in Your Projects
45mTest Driven Prompt Programming: How AI is Changing the Way We Code
47mThe Art of Prompt Engineering: Best Practices for Effective AI Interactions
51mChatGPT as a developer's personal servant
29mSupercharge Your Productivity: Mastering Prompt Engineering
46mBreaking AI: Live coding and hacking applications with Generative AI
45mPanel Discussion on AI for Code Generation
58mAI, Determinism, Code Generation and Refactoring