AI Usage Policy

I have a side project, git-prompt-story to attach Claude Vode session in GitHub git notes. Though it is not that simple to do automatic (e.g. i need to redact credentials).

Re: AI Usage Policy

#7

Post by embedding-shape » Fri, Jan 23, 2026, 10:57 AM UTC

christoph-heiss wrote: post #3

mefengl wrote: post #2

[flagged]

Not sure why you are getting downvoted, given that the original site is such a jarringly user-hostile mess.

Without using a random 3rd party, and without the "jarring user-hostile mess":

https://raw.githubusercontent.com/ghostty-org/ghostty/refs/h...

Re: AI Usage Policy

#8

Post by radarsat1 » Fri, Jan 23, 2026, 10:59 AM UTC

jakozaur wrote: post #6

See x thread for rationale: https://x.com/mitchellh/status/2014433315261124760?s=46&t=FU... “ Ultimately, I want to see full session transcripts, but we don't have enough tool support for that broadly.” I have a side project, git-prompt-story to attach Claude Vode session in GitHub git notes. Though it is not that simple to do automatic (e.g. i need to redact credentials).

I've thought about saving my prompts along with project development and even done it by hand a few times, but eventually I realized I don't really get much value from doing so. Are there good reasons to do it?

Re: AI Usage Policy

#9

Post by arjunbajaj » Fri, Jan 23, 2026, 11:02 AM UTC

I can see this becoming a pretty generally accepted AI usage policy. Very balanced.

Covers most of the points I'm sure many of us have experienced here while developing with AI. Most importantly, AI generated code does not substitute human thinking, testing, and clean up/rewrite.

On that last point, whenever I've gotten Codex to generate a substantial feature, usually I've had to rewrite a lot of the code to make it more compact even if it is correct. Adding indirection where it does not make sense is a big issue I've noticed LLMs make.

Re: AI Usage Policy

#10

Post by fragmede » Fri, Jan 23, 2026, 11:05 AM UTC

radarsat1 wrote: post #8

jakozaur wrote: post #6

See x thread for rationale: https://x.com/mitchellh/status/2014433315261124760?s=46&t=FU... “ Ultimately, I want to see full session transcripts, but we don't have enough tool support for that broadly.” I have a side project, git-prompt-story to attach Claude Vode session in GitHub git notes. Though it is not that simple to do automatic (e.g. i need to redact credentials).

I've thought about saving my prompts along with project development and even done it by hand a few times, but eventually I realized I don't really get much value from doing so. Are there good reasons to do it?

It's not for you. It's so others can see how you arrived to the code that was generated. They can learn better prompting for themselves from it, and also how you think. They can see which cases got considered, or not. All sorts of good stuff that would be helpful for reviewing giant PRs.