Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Vibing a non-trivial Ghostty feature

mitchellh.com

Post reply on HN
Print view View original

111–120 of 160 posts

Re: Vibing a non-trivial Ghostty feature

#111

Post by j45 »

austinjp wrote: post #33
XenophileJKO wrote: post #26

Earlier quoted context omitted.

Yes, this. If you can describe why it is slop, an AI can probably identify the underlying issues automatically. Done right you should get mostly reasonable code out of the "execution focused peer".

In climate terms, or even simply in terms of $cost, this very much feels like throwing failing on a bonfire. Should we really advocate for using AI to both create and then destroy huge amounts of data that will never be used?

Who said anything about advocating for it.

What can keep up with the scale of it?

We know that AI is more capable by what's input into it for the prompt side so chances are code review might be a little more sensible.

Maybe this comment/idea will be a breakthrough in improving AI coding. :p

Re: Vibing a non-trivial Ghostty feature

#112

Post by j45 »

yggdrasil_ai wrote: post #110
XenophileJKO wrote: post #26

Earlier quoted context omitted.

Yes, this. If you can describe why it is slop, an AI can probably identify the underlying issues automatically. Done right you should get mostly reasonable code out of the "execution focused peer".

> If you can describe why it is slop, an AI can probably identify the underlying issues automatically I would argue against this. Most of the time the things we find in review are due to extra considerations, often business, architectural etc, things which the AI doesn't have context of and it is quite bothersome to provide this context.

I generally agree that vague 1 shot prompting might vary.

I also feel all of those things can be explained over time into a compendium that is input. For example, every time it is right, or wrong, comment and add it to an .md file. Better yet, have the CLI Ai tool append it.

We know what is included as part of a prompt (like the above) is more accurately paid attention to.

My intent isn't to make more work, it's just to make it easier to highlight the issues with code that's mindlessly generated, or is overly convoluted when a simple approach will do.

Re: Vibing a non-trivial Ghostty feature

#114

Post by sqs »

moderation wrote: post #107
jebarker wrote: post #80

Earlier quoted context omitted.

It was this one: https://sourcegraph.com/blog/dev-tool-time-mitchell-hashimot... They even used the quote as the title of the accompanying blog post. As I say, I didn’t mean this as a gotcha or anything- I totally agree with the change and I have done similarly. I’ve always disabled autocomplete, tool tips, suggestions etc but now I am actively using Cursor daily.

The CEO of Sourcegraph Quinn was pretty negative on coding agents and agentic development only about 10 months ago [0]. He had 'agentic stuff' in the Deader category (Used rarely, Reviewing it aint worth it). In fairness, he did say it was the future but 'is not there yet'. Since then, Sourcregraph's code assistant plugin Cody has been deprecated an they are all in on agents and agentic with Amp. 0. https://youtu.be/…

Yeah, I said about coding agents, “it’s obviously the future, but it’s not there yet”. That talk was from the AI Engineer conference in June 2024 (16 months ago). Coding agents have come a long way since then!

Re: Vibing a non-trivial Ghostty feature

#115

Post by osigurdson »

>> AI is very good at fill-in-the-blank or draw-the-rest-of-the-owl.

This is definitely the sweet spot imo. Any time I've been able to come up with a solid, hand coded pattern and have AI repeat in several similar areas has been the most rewarding experiences that I have had with it.

Re: Vibing a non-trivial Ghostty feature

#117

Post by thaumasiotes »

osigurdson wrote: post #115

>> AI is very good at fill-in-the-blank or draw-the-rest-of-the-owl. This is definitely the sweet spot imo. Any time I've been able to come up with a solid, hand coded pattern and have AI repeat in several similar areas has been the most rewarding experiences that I have had with it.

By the time you've done that, why not repeat it yourself?

I once needed to define a large table of trigrams in C (for the purpose of distinguishing "English" from "not English"). Setting it up looked like this:

1. Download a book from Project Gutenberg.

2. Write something that went through the book character-by-character, and for every character, remembered the trigram ending there.

3. Make the form of "remembering" be "append a line of code to this file that says `array[char1][char2][char3] = 1`".

4. Now I have a really long C file that compiles into the dictionary I want.

It sounds to me kind of like you want to replace step 3 with an LLM. If that's right... what value is the LLM adding?

Re: Vibing a non-trivial Ghostty feature

#120

Post by osigurdson »

thaumasiotes wrote: post #117
osigurdson wrote: post #115

>> AI is very good at fill-in-the-blank or draw-the-rest-of-the-owl. This is definitely the sweet spot imo. Any time I've been able to come up with a solid, hand coded pattern and have AI repeat in several similar areas has been the most rewarding experiences that I have had with it.

By the time you've done that, why not repeat it yourself? I once needed to define a large table of trigrams in C (for the purpose of distinguishing "English" from "not English"). Setting it up looked like this: 1. Download a book from Project Gutenberg. 2. Write something that went through the book character-by-character, and for every character, remembered the trigram ending there. 3. Make the form of "remembering"…

Concretely, I was creating a cli application. I had implemented a few commands end-to-end and established some solid patterns. I used Codex (i.e. the PR creating flavor) to provide instructions and get it to review the existing patterns before continuing as asked it to rigorously follow them. I had to do about ~10 more things and it worked really well. It was easy for me to review and understand because I already knew the pattern and it seemed easy for it to get right.

It worked so well that I am always trying to look for opportunities like this but honestly, it isn't that common. Many times you aren't creating a pattern and repeating - you are creating a new pattern. AI is good to chat with to get ideas and come up with an approach in these situations seems to be more effective to me.

Post reply on HN