←back to thread

Show HN: I built a toy music controller for my 5yo with a coding agent

(github.com)
37 points JeffMcCune | 3 comments | 08 Jul 25 14:32 UTC | HN request time: 0.212s | source

The HN community may find the context of the prompts, organized by each turn in each session, the most useful. See the website/docs/prompts.md and session-X.md files. I also started exploring some workflows for the LLM to execute, organized in the website/docs/tasks/ folder. I found it pretty handy to have the LLM document our work as we went and simply embedded the static site into the executable, along with all the music and logic.

The whole project took me about a day for the backend. The C++ controller itself took only a few turns.

I enjoyed focusing on my son's experience and letting the agent handle the C++, Javascript, and Go code.

I'm still getting started with coding agents, so please do share any tips or tricks to help me with similar projects. I'm most interested in how to work effectively with the agent, like what you see in dev-loop.sh

1. x______________ ◴[12 Jul 25 10:48 UTC] No.44541047[source]▶
>The HN community may find the context of the prompts, organized by each turn in each session, the most useful.

So cool! I'll review fully later but was curious as something caught my attention, do you need to say please and thanks in your prompts for better outputs or is this just anthropomorphism taking over?

replies(2): >>44542048 #>>44542514 #
2. nick__m ◴[12 Jul 25 13:47 UTC] No.44542048[source]▶
I do the same! To me it's a semi sarcastic hedge against the robots uprising and Roko's basilisk.

But more seriously I remember reading somewhere the LLM produce better output with question starting with please, supplementary politeness was not improving results. Probably because the training corpus include many samples where politeness in request produce better response. That apply to the original GPT-3.5, how it applies to newer models your guess is as good or better then mine...

The thanks are unnecessary but I guess they are useful to reinforce his son politeness habits.

3. JeffMcCune ◴[12 Jul 25 14:57 UTC] No.44542514[source]▶
It’s anthropomorphism taking over. I pretend I’m talking with a colleague when I do this sort of thing.