←back to thread

728 points freetonik | 5 comments | | HN request time: 0s | source
Show context
philjohn ◴[] No.44977150[source]
I like the pattern of including each prompt used to make a given PR, yes, I know that LLM's aren't deterministic, but it also gives context of the steps required to get to the end state.
replies(4): >>44977198 #>>44979222 #>>44980141 #>>44980617 #
Filligree ◴[] No.44979222[source]
It's ridiculous and impractical, honestly. A single AI-generated PR would likely involve at least 10-20 prompts, interspersed with testing, manual edits to context / guideline files without which those prompts don't have the same effect, manual coding, and more. A screen recording would do better.
replies(1): >>44979691 #
1. asdff ◴[] No.44979691[source]
Is there really no logging capability with these tools that would track all of that prompting/testing/editing/inputting?
replies(1): >>44980023 #
2. Filligree ◴[] No.44980023[source]
Sure, screen recorders exist.

And if contributions are that unwelcome, then it's better not to contribute. There has to be some baseline level of trust that the contributor is trying to do the right thing; I get enough spying from the corporations in my life.

replies(1): >>44980812 #
3. asdff ◴[] No.44980812[source]
I'm not talking screen recorder but a log file where I could be given it and use it for input and repeat the work exactly as it was done. Sort of like how one could do the same with their bash history file to repeat an initially exploratory analysis effort using the same exact commands. I'm surprised that isn't already a capability given the business interest with AI. One would think they would like to cache these prompt flows to ensure long term fidelity in process.
replies(1): >>44985132 #
4. Filligree ◴[] No.44985132{3}[source]
Does that exist for VSCode?

If not, why would it exist for VSCode + a variety of CLI tools + AI? Anyhow, saving the exact prompt isn't super useful; the response is stochastic.

replies(1): >>45002753 #
5. asdff ◴[] No.45002753{4}[source]
VScode has a history capability. You can't save a prompt + a seed to recover the response? That seems like it would be highly useful.