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

ASCII-Driven Development

medium.com

Post reply on HN
Print view View original

61–70 of 97 posts

Re: ASCII-Driven Development

#61

Post by alt187 »

stephc_int13 wrote: post #57

Argh. I may suffer from some kind of PTSD here, but after reading a few lines I can't help but see the patterns of LLM style of writing everywhere in this article.

Holy cows, same. But it's not PTSD. People think you can tell because of ternary rhythm, —, big-words and other shenanigans. These are tactics over strategy, obsessing over the minutiae. But I think what you're feeling (and what I sure fucking am) is a lack of voice.

This writing says something, has a point, and you could even say it has a correct way to get to the point, but it lacks any voice, any personality. I may be wrong -I stopped reading midway- but I really don't think so.

Re: ASCII-Driven Development

#63

Post by alehlopeh »

tptacek wrote: post #56
mrstackdump wrote: post #53

Earlier quoted context omitted.

Maybe I'm not understanding it (totally possible!) but could Claude just do that by reading standard out and writing to standard in?

I had a really hard time getting anything like that to work (you can't just read stdout and write stdin, because you're driving a terminal in raw mode), but it took like 3 sentences worth of Claude prompt to get Claude to use tmux to do this reliably.

I tell Claude code to use an existing tmux session to interact with eg a rails console, and it uses tmux send-keys and capture-pane for IO. It gets tripped up if a pager is invoked, but otherwise it works pretty well. Didn’t occur to me to tell it to take screenshots.

Re: ASCII-Driven Development

#64

Post by tptacek »

alehlopeh wrote: post #63
tptacek wrote: post #56

Earlier quoted context omitted.

I had a really hard time getting anything like that to work (you can't just read stdout and write stdin, because you're driving a terminal in raw mode), but it took like 3 sentences worth of Claude prompt to get Claude to use tmux to do this reliably.

I tell Claude code to use an existing tmux session to interact with eg a rails console, and it uses tmux send-keys and capture-pane for IO. It gets tripped up if a pager is invoked, but otherwise it works pretty well. Didn’t occur to me to tell it to take screenshots.

`tmux capture-pane`.

Re: ASCII-Driven Development

#65

Post by nmstoker »

sedatk wrote: post #23

Off-topic but I’m so happy to have moved out of Medium.

Curious to understand what drove that the most? Certainly for this article, Medium's annoying way it blocks zooming in/out on images when on mobile is limiting and frustrating! But I sense you'll have broader concerns...

Re: ASCII-Driven Development

#66

Post by alehlopeh »

tptacek wrote: post #49
electroly wrote: post #47

Earlier quoted context omitted.

Can you explain tmux's contribution here? I'm confused why this process wouldn't work just the same if CC directly executed the program rather than involving tmux. Are you just using tmux to trick the program under test into running its TUI instead of operating in a dumb-stdout mode?

It allows Claude to take screenshots and generate keyboard inputs. It's like TUI Playwright.

So by screenshots you mean tmux capture-pane, not actual screenshots. So in essence it is using stdout, just not Claude’s own.

Re: ASCII-Driven Development

#67

Post by facorreia »

Good idea to build low-fidelity mockups. SVG in my opinion is a better format for this job than text. For instance, in the screenshots from the article, not a single example is properly aligned. That is distracting and makes these assets hard to share.

Re: ASCII-Driven Development

#68

Post by muzani »

arglebarnacle wrote: post #14

A really interesting article, and I'm likely to give it a shot a work. I'm grateful for it, and yet I found it difficult to get through because of a sense of "LLM style" in the prose. I won't speculate on whether the post is AI-written or whether the author has adopted quirks from LLM outputs into their own way of writing because it doesn't really matter. Something about this "feeling" in the writing causes me discom…

I stopped reading it at that point. I'm not against AI-written articles; I even think it's a little rude to accuse. But I agree.

I think we do develop "antibodies" against this kind of thing, like listicles, clickbait, and random links that rickroll you. It's the same reason the article isn't titled, "5 examples of ASCII-Driven Development. You'll never guess #2!"

Every article is a little mentor, and the thing with mentors and teachers is you have to trust them blindly, suspend disbelief, etc. But the AI voice also triggers the part of the brain designed to spot scams.

Re: ASCII-Driven Development

#69

Post by CompoundEyes »

Recently I was using docling to transform some support site html into markdown and replacing UI images with inline descriptive text. An LLM created all the descriptions. My hope was descriptions like “a two pane..below the hamburger…input field with the value $1.42…” would allow an LLM to understand the UI when given as context in a prompt. Maybe I could just put ASCII renderings inline instead.

Re: ASCII-Driven Development

#70

Post by jbmsf »

I like the idea but I think it's going to be hard to put this particular genie back in the bottle. As an engineering leader, I prefer low fidelity designs early on, but practically no one else in my company wants that.

Designers have learned figma and it's the de facto tool for them; doing something else is risky for them.

Product leaders want high fidelity. They love the AI tools that let them produce high fidelity prototypes.

Some (but not all) engineers prefer it because it means less decision making for them.

Post reply on HN