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

Claude, change the “Add to Cart” button to blue

opusfived.dev

Post reply on HN
Print view View original

301–310 of 449 posts

Re: Claude, change the “Add to Cart” button to blue

#301

Post by inerte »

selestify wrote: post #232
plorkyeran wrote: post #146

Earlier quoted context omitted.

Yeah, if this is how people interact with claude I’m not surprised they’re having a bad time in ways that I don’t. Asking it why it did something or getting combative is a waste of time.

How does one learn to interact with Claude more effectively?

This is a good resource https://howborisusesclaudecode.com/

My best takeaway from the site was: Every time you see Claude Code / Codex doing something you don't want, ask it to add to AGENTS.md. Specially if they churn a lot doing something, and eventually find a way. I ask it to store the way it made something work. It's a constant gardening of AGENTS.md and it has really working well.

Re: Claude, change the “Add to Cart” button to blue

#302

Post by GreenWatermelon »

JohnMakin wrote: post #191

> Worth naming: the Add to cart button is still black. Got an audible guffaw out of me. This really is what the experience is like sometimes if you're just giving it a result without being specific in implementation, and it comes out of nowhere, some days much worse than others. I've become patient with it, but whatever this style of output is called or doing - it is both condescending and entirely unhelpful, and it…

I've come to call this language "Claudese English" (or Claudish)

Recently I've started using GLM models and noticed they aren't very claudish (just a little bit, compared to DeepSeek which is extremely claudish)

Re: Claude, change the “Add to Cart” button to blue

#303

Post by Sohcahtoa82 »

brap wrote: post #16

How do you manage your frustration in these interactions? I often find myself getting pissed off

If you know how to write it manually, then do it.

In my experience, Claude Code is great at making a first-pass at a project, but once you start asking it to make changes, it explodes. A bug fix that should only be 2 lines turns into adding 3 functions totaling 100 lines.

Something as simple as "make the button blue" should be done manually.

Re: Claude, change the “Add to Cart” button to blue

#304

Post by Bjartr »

selestify wrote: post #235
catapart wrote: post #102

Earlier quoted context omitted.

same. none of the available prompts are what I would prompt claude with and I get way better results than this. makes sense to me why the provided prompts result in the simulated outcomes. garbage in, garbage out.

So how would you prompt it instead? Because that's exactly how I prompt it, because any reasonable human being would know exactly what I mean by "Make the shopping button blue", and I am sick and tired of getting shitty results.

The first prompt is fine, it's the following ones that are poor.

> Why is half the site blue now? I asked you to change one button.

> Half the site is blue. I asked for ONE button

Neither of these is an instruction to fix the problem, they're treating the AI like a person and telling it what it did wrong, expecting the implied admonishment to be enough to steer it back. But without an actual instruction, it just goes and does whatever it thinks will help, which is often arbitrary.

The response I would have used in this situation is

"The Cancel button is also blue now. Make sure the color change is only scoped to the Add to Cart button"

Most of the available responses throughout this "skit" are similar cases of expressing frustration first and guiding the result second.

Skip the emotion and say exactly what you want, and nothing besides that.

Re: Claude, change the “Add to Cart” button to blue

#305

Post by autoexec »

varispeed wrote: post #125
captainbland wrote: post #40

This is actually what keeps people using AI: variable reward schedule. It's basically gambling.

Something regulators should look at. They don't deliver consistent compute, yet charge consistent money. In my opinion that's fraud.

Maybe they should be regulated like lootboxes and be required to post odds.

Re: Claude, change the “Add to Cart” button to blue

#306

Post by theshrike79 »

bahbahbahbah wrote: post #295
dudeinhawaii wrote: post #164

Great site, triggered memories! haha. To try to add something to this discussion -- I think that while I've seen these sort of loops less --- what I have seen is "overly helpful". Models nowadays want to double-triple-quadruple check things. I'm being silly but it verges on "I have a working solution but let me write a variation in Rust to ensure a convergent solution and prove this works". I've had to stop models no…

Plus rigorously ensuring backwards compatibility for a project that is 2 hours old and has zero users.

This is why I have a PROJECT.md in all my repos, which specifically reiterates that this is a greenfield single user project that never leaves my LAN.

It tends to relax some of the insane things LLMs tend to do.

Re: Claude, change the “Add to Cart” button to blue

#307

Post by dpark »

jodrellblank wrote: post #294
dpark wrote: post #160

Earlier quoted context omitted.

I see this sentiment pretty regularly, and I don’t get it. Variable rewards is not sufficient to establish that it is “ basically gambling”. Everything in life is variable reward. You invite a friend over, they might accept or they might not. Drive to work, traffic might be good or might be bad. You ask a colleague to finish a task, they might do it or might not or might do a good job or might not. Everything is vari…

> " Everything is variable reward. Is everything gambling? " well, no. If you work overtime and get paid overtime, you are not gambling and that is not a variable reward. Humans engage more with rewards that are intermittent and variable. Like Futurama's scene from 'The Scary Door' where the character says "A casino where I'm winning, I must be in heaven! A casino where I always win, that's boring, I must really be I…

> A constant predictable reward is boring, less engaging.

Perhaps but predictable outcome is a very desirable quality. No one wants a hammer that sometimes drives nails and sometimes doesn’t. All of the current harness engineering work is about squeezing predictability out of the LLM.

> Good traffic is not a "reward" for driving to work(!)

Like hell it’s not. I drove into work last Friday and there was no traffic because of the holiday weekend. It was amazing. Had me considering whether Friday should be one of my standard RTO days.

Re: Claude, change the “Add to Cart” button to blue

#308

Post by qlte »

dpark wrote: post #276
rnjesus wrote: post #259

Earlier quoted context omitted.

i agree with you that it’s principally different from a slot machine, and that it’s possible to use it in a way (like you describe) that is much more focused, for lack of a better term, to great effect most people don’t use ai this way though, and i still feel like the end-psychological reward mechanism is very, very similar to gambling regardless of how well one utilizes it (and this is even more obvious with image…

> most people don’t use ai this way though How do they use it? Surely no one is just repeating the same prompt over and over (except as a Ralph loop perhaps, which is automated). I’m really struggling with the notion that most people just throw the same prompt repeatedly hoping it eventually works. Because that doesn’t sound like gambling. It sounds crazy (and frustrating). > and i still feel like the end-psychologic…

When working on a problem models will walk you down a garden path requiring only yes/no answers or very brief clarifications for a long time. It's always proposing its own workarounds/suggestions/etc. Especially if trying to debug something where it has more understanding than the user so really all it needs from you is "uh sure try that too I guess" from time to time.

And sometimes the debugging has already veered completely off course at the beginning so it's futile, but each time the fleeting hope that just a few thousand more tokens will magically fix it tempts you to keep going a little longer.

Re: Claude, change the “Add to Cart” button to blue

#309

Post by rnjesus »

dpark wrote: post #276
rnjesus wrote: post #259

Earlier quoted context omitted.

i agree with you that it’s principally different from a slot machine, and that it’s possible to use it in a way (like you describe) that is much more focused, for lack of a better term, to great effect most people don’t use ai this way though, and i still feel like the end-psychological reward mechanism is very, very similar to gambling regardless of how well one utilizes it (and this is even more obvious with image…

> most people don’t use ai this way though How do they use it? Surely no one is just repeating the same prompt over and over (except as a Ralph loop perhaps, which is automated). I’m really struggling with the notion that most people just throw the same prompt repeatedly hoping it eventually works. Because that doesn’t sound like gambling. It sounds crazy (and frustrating). > and i still feel like the end-psychologic…

> How do they use it?

as an example, i was using chatgpt a few weeks back to help me remember the name of a painting i’d seen about a decade ago. i could recall the general shape of the subject and that it was europeanish, but nothing else. after seven turns or so it finally got it, and honestly, the relief of finally remembering the name felt like, well, hitting a jackpot

i’ve had a similar feeling of success after trying to get it to give a comprehensible answer when asking it for a solid counter-argument to philosophical questions. it is indeed often crazy and frustrating

> but I get the same reward when I code by hand

i have only done very simple coding work with llms, so that may be why our ideas differ about the feeling of reward. this is where the comparison to gacha makes more sense than slots, since when you’re coding, you still get a reward each turn whilst chasing the final/desired result

Re: Claude, change the “Add to Cart” button to blue

#310

Post by CookieCrisp »

qurren wrote: post #217
dudeinhawaii wrote: post #164

Great site, triggered memories! haha. To try to add something to this discussion -- I think that while I've seen these sort of loops less --- what I have seen is "overly helpful". Models nowadays want to double-triple-quadruple check things. I'm being silly but it verges on "I have a working solution but let me write a variation in Rust to ensure a convergent solution and prove this works". I've had to stop models no…

One thing it's missing: "smoking guns" and "smoke tests" If you search my company's Slack for "smoke" the results are almost all within the past 2 years ...

And storing memories for every “footgun” it finds, while removing more important memories (or shortening them until they’re inaccurate or useless)
Post reply on HN