ai(4/0)
Development patterns with ai
In Hrishi Olickel’s LLM Hacker Guide he describes some of the ways his thoughts about the development process have changed since working closely with Large Language Models (LLMs). Development Process Hrishi explores the ways that the development process has changed. He offers two other in-between processes, but below is the traditional and the new AI methodology. flowchart LR Write -- Compile -- Run flowchart LR Chat -- Play -- Loop -- Nest Traditional development is about writing code, compiling it, and running it.…
Writing with ai
Inspired by Ethan Mollick’s newsletter today (I Cyborg, Using Co-Intelligence), I attempted a co-intelligence writing test of my own. I’d jotted some thoughts about belonging in my Bullet Journal that I thought could become an article, but I felt some hesitancy to tackle it lest I get stuck on such a broad topic. First, I dictated my scribbles into a digital note. Then I shared the results with an LLM and asked for a short summary, suggested resources on my main topics, and a revised version of my writing.…
Thoughts on AI
In Software Development James Somers writes a thoughful piece about the effect that models like ChatGPT are having on his work and perception of future programming. He delves into the fears associated with this “tsunami” change but ends with a hopeful note by comparing the effect of LLMs on chess.
Prompt engineering for developers
(these notes originate from Jeff Mitchell’s presentation at Performance Trust). Prompt Engineering Tips use delimiters to instruct the model which text to work upon (and which to ignore). request structured output (JSON, CSV, Markdown, etc). offer a way out if the input does not meet certain criteria. give the model more context and supply steps. Reduces errors, especially in deductive reasoning. Specify how the output should look. request that the model complete the solution before supplying an answer.…