10x Development: LLMs For the working Programmer
summary
Practical workshop showing concrete workflows: transform meeting transcripts into YAML GitHub issues and Slack notifications, generate small helper scripts (pcap→YAML, clipboard cleaners), and scaffold UI prototypes and DSLs that produce runnable HTML/JS. Recommends using gpt-4o and claude 3.5 sonnet, reports ~6,000 GitHub contributions driven by LLMs, and uses a 100-line tool prompto to manage prompt fragments. Demonstrations include a reality‑TV style code review, Arduino RTOS sketch, and multiple quick prototypes; no AutoGPT/agent reliance, outputs usually need only minor edits.
AI-written summary · about
chapters (7)
- 0:00Welcome to LLMs for programming
- 10:50Hands-on techniques
- 25:25LLMs as code translators
- 41:16Creative LLM applications
- 57:56Simulating app existence
- 1:06:03Managing LLM workflows
- 1:12:43Q&A
related talks
19mHacking Productivity with LLMs
24mLLMs: Powering Lightning Fast Product Innovation
15mAutomating menial engineering tasks with LLMs
44mJoint Keynote Address: Accelerating Software Development: The LLM (R)evolution
01h 00mFrom LLM Theory to Practical Agentic Implementations
01h 36mLearning To Stop Writing C++ Code (and Why You Won’t Miss It)
01h 39mMastering LLMs: From Prompt Engineering to Agentic AI
10mRethinking collaboration: LLMs, teams, and cognitive load