Coding with AI

lap around neural nets and LLM concepts to understand how to use them for coding effectively

Transcript

1. Coding with AI May 2025
2. "Evolution, Morpheus. Evolution! Like The Dinosaur. Look Out That Window. You've Had Your Time. The Future Is OUR World, Morpheus. The Future Is OUR Time."
3. Becoming Neo May 2025
4. Agenda • Getting intuition for the technology and buzzword • How to maximize value from working with AI and what are the limitations
5. So let’s start with the basics where 𝑎∈1...𝐴 is the head number, and 𝑓 is some function like RELU or whatever and the 𝐛s are biases (𝑀 is the attention mask and 𝑑 𝐸is the size of the embedding). the output of layer 𝑙∈1...𝐋, 𝐗𝐥 is ,
6. LMM - Large Language Model • Large - trained on a huge data set and uses a huge number of parameters • Language - geared toward understanding language ( • Model - a type of Neural Network
7. Ok - so the real basics Preceptron (1957)
8. Network
10. Network https://playground.tensorflow.org
11. embeddings https://projector.tensorflow.org/
12. Self Supervised Learning The quick brown fox jumps over the _____ The quick brown fox jumps over the _____ dog The _____ brown fox jumps over the lazy dog
13. Attention Attention helps helps a neural network link related words Handle disambiguation • Lexical- e.g. flies as verb vs. part of noun , understand the like is related to arrow/banana • Structural (fruit-flies is a unit) Time flies like an arrow; fruit flies like a banana
14. Consequences • The main algorithm is next work (actually part of word) prediction ◦ What we get is an option • Common things are easy - if you are using common practices, working on areas that have a lot of good example, chances are AI can really push you fast ◦ The corollary is that if you have unique patterns in your code, completely novel area AI will struggle • Getting exactly what you want is hard • Probable != Correct (aka “hellucinations”) • CONTEXT is king
15. https://github.com/vectara/hallucination-leaderboard
16. Context is king!
18. Agent
19. MCP Model Context Protocol (but there’s already AI in API)
20. RAG - Retrieval Augmented Generation • Used to be a pre-process to enrich the context - now it is basically a big MCP for Search • Helps bring relevant data (to help with Attention) • Enforces permissions over data
21. Consequences • The main algorithm is next work (actually part of word) prediction ◦ What we get is an option • Common things are easy - if you are using common practices, working on areas that have a lot of good example, chances are AI can really push you fast ◦ The corollary is that if you have unique patterns in your code, completely novel area AI will struggle • Getting exactly what you want is hard • Probable != Correct (aka “hellucinations”) • CONTEXT is king
22. Sample Rules
23. “Never Send A Human To Do A Machine's Job.“
24. What’s a “machine job” then? • Write Unit test • Check coverage • Verify Standards • Scan for vulnerabilities • Convert Figma to code • Alot more
25. But remember • Simple refactoring are much harder for an LLM - they don’t copy paste, the regenerate so big refactoring can be risky • Don’t try big things if you/LLM didn’t also write down all the tasks (e.g. in an MD file) the attention can break
26. Feedback loop • Long contex ◦ hard to hold attention on the right thing ◦ Increase odds for hallucination (we predict on prediction rather on concrete knowledge) • So create contexts often, work in small increments • Don’t hesitate to git commit successful interim steps
27. “We Can Never See Past The Choices We Don't Understand.”
28. LLM can also help you understand • The code you or someone else wrote • The essence of documentation (sometimes via tools) • The plan before making changes • Nuances of the code you or you and the LLM just created • Trace why something is broken • Analyze profiling data (CPU/ memory )
29. RISKS The S in LLM/MCP stands for security Once only Claude and I knew what this code does.. now.. Endless POC level code
30. “I Know Kung-Fu” (or do I)
31. Putting it all together • (modified) RIPER framework • Structured Workflow: Clear separation of development phases, with Research and Innovate unified for a streamlined discovery and ideation process. • Memory Bank: Persistent documentation across sessions • State Management: Explicit tracking of project phase and mode
36. "I Don't Know The Future. I Didn't Come Here To Tell You How This Is Going To End. I Came Here To Tell You How It's Going To Begin.