Mastodawn

Wrote up about my personal journey from AI skeptic to someone who finds a lot of value in it daily. My goal is to share a more measured approach to finding value in AI rather than the typical overly dramatic, hyped bait out there. https://mitchellh.com/writing/my-ai-adoption-journey

My AI Adoption Journey

Mitchell Hashimoto

Show thread

Bogdan Buduroiu Feb 6

@mitchellh I thought letting agents roam wild would work eventually and I could shepherd them as I would a junior sending me PRs for review. This, unfortunately, didn't work for me.

I ended up using smaller, "dumber" models that I could theoretically self-host (GLM-4.7, Qwen-3-Coder-Next) and working in a tighter loop with them (I design the interface, they fill it in).

Primeagen's 99 tool was a big big saviour here

Show thread

/c64/youth.sid Feb 7

@budududuroiu @mitchellh I am on a similar journey. Now focussing on how to define a good agent. It is working out to create simple, focussed agents that can do one task well. It’s a bit counterintuitive but it has to do with. 1. Choosing the right model and temperature 2. Limiting context by having a system prompt focussed on the one task. 3. Limiting the tools it can use and the information it can access. And keep tweaking that. Often I do that by letting the agent modify its own system prompt

Show thread

Bogdan Buduroiu Feb 7

@yth @mitchellh interesting on the modifying system prompt route. How are the results of your experiments with that?

Show thread

/c64/youth.sid

@[email protected] @mitchellh Basicly I tell the agent what I want from it and put that in to markdown in “its own words”. Tell it to shape the prompt in such a way that it will help it help me. And keep it compact. So it’s not doing it autonomously, I just use the agent to develop its own system prompt.