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

71–80 of 97 posts

Re: ASCII-Driven Development

#71

Post by iamanllm »

oasisbob wrote: post #34
iamanllm wrote: post #24

Earlier quoted context omitted.

"Not as an aesthetic choice. Not as nostalgia. But as a thinking tool " is a perfectly normal sentence, and I think there is an equally bad trend of people assuming things are AI written and forget that AI was trained on human writing. But to your point, agreed there is a disconnect when things are in fact written by AI, but I skimmed the article anyway so to me it didn't matter lol.

Those are sentence fragments, not perfect sentences. They're useful in some contexts, but are inappropriate for more formalized writing. When LLMs reuse the same patterns dozens of times in a single article, the patterns stops being interesting or surprising and just become obnoxious and grating.

it's not formal writing it's a blog post.

Re: ASCII-Driven Development

#72

Post by stormy »

Most ascii/unicode based diagrams spit out by AI have misaligned boxes, similar to the ones generated in the article.

I’m not affiliated, but to clean them up you can use something like ascii-guard (https://github.com/fxstein/ascii-guard) which is a linter that will clean it up. Beats doing it by hand after multiple attempts telling AI to do it and repeatedly fail.

Re: ASCII-Driven Development

#73

Post by tom_ »

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 just give up the moment I notice it. I gave up on this one once I got to "The High Fidelity Trap". My LLMdar said: brrrrrp. (Imagine the sound of a sad trombone, only out of tune.) If I feel like the author couldn't be bothered to write it, I feel like I can't be bothered to read it.

And if I'm wrong: so be it. I'm comfortable living dangerously.

(Reading it again, I probably should have noticed by "But here’s the thing: AI-generated UIs are high-fidelity by default", a couple of sentences previously. And in fact, there's "Deliberately sketchy. Intentionally low-fidelity. The comic-sans-looking wireframes were a feature, not a bug" in the very first paragraph - god, I'm so stupid! Still, each time I get this wrong, I'm that bit more likely to spot it in future.)

Re: ASCII-Driven Development

#74

Post by joshribakoff »

nmstoker wrote: post #65
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...

For me, I’m simply trying to read the article and there are random full screen pop-ups nagging me to sign up for newsletters and stuff

Re: ASCII-Driven Development

#76

Post by _sinelaw_ »

mrstackdump wrote: post #60
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 would love to see your prompt if you ever post it anywhere.

For Claude, it's enough to prompt "use tmux to test", that usually does the work out of the box. If colors are important I also add "use -e option with capture-pane to see colors". It just works. I used it regularly with Claude and my TUI. For other agents other than Claude I need to use a more specific set of instructions ("use send-keys, capture-pane and mouse control via tmux" etc.)

Since I have e2e tests, I only use the agent for: guiding it on how to write the e2e test ("use tmux to try the new UI and then write a test") or to evaluate its overall usability (fake user testing, before actual user testing): "use tmux to evaluate the feature X and compile a list of usability issues"

Re: ASCII-Driven Development

#77

Post by Tenobrus »

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…

some ai detectors work now. pangram detects this as 57% AI written, and the parts it thinks are human are.... the ascii diagrams / screenshots. all the actual text it detects as generated.

Re: ASCII-Driven Development

#78

Post by ynac »

nihiven wrote: post #20

I like to make these kinds of mock ups using https://asciiflow.com . Some of the components from the article paste nicely there.

Monodraw is a champ as well. Stand alone and outputs to graphic or text file. Easy to feed to other people or artificial people.

Re: ASCII-Driven Development

#79

Post by wakawaka28 »

alehlopeh wrote: post #66
tptacek wrote: post #49

Earlier quoted context omitted.

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.

"In essence" but terminals do stuff to render stdout that you do not want a LLM to have to replicate, I think. If your TUI does stuff in fullscreen or otherwise with a bunch of control codes, that is simple work for a terminal but potentially intractable for a LLM.

Re: ASCII-Driven Development

#80

Post by batisteo »

mixmastamyk wrote: post #5

Like the idea, but this is definitely Unicode and not ASCII. It's hard to believe someone finished a piece of this length but still misunderstood, especially when some examples have emoji in them. Alternately, they chose a misleading name on purpose. Why? Someone mentioned TUI, which sidesteps the issue entirely.

I totally agree. It's called Plain Text.
Post reply on HN