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

341–350 of 455 posts

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

#341

Post by ceejayoz »

selestify wrote: post #244
ceejayoz wrote: post #19

Earlier quoted context omitted.

The goal of my personal harness is to get to the point where I never actually talk to Claude directly for that very reason.

Is your harness available for install somewhere? Surely you still have to give feedback to Claude. How do you do that without talking to Claude directly? By using a different model? But wouldn't that AI have no more common sense than Claude?

It's extremely bespoke.

Initial dev required talking to Claude. Now I add a ticket in the board, it makes me a mockup/writeup, I approve, and it gets me a temporary webserver, iOS/Android build, etc. to verify it.

Review loops, agents that enforce my pet peeves and testing/debugging processes, etc. all run automatically... and then Codex strips down the prose at the end. There's not zero AI generated output, but it's already been critiqued and verified by a whole cluster of independent actors before it gets to me. When I have feedback, I file a ticket.

I wanted to get out of the "what the fuck, why?!" loop. Now I let the agents handle that.

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

#344

Post by commandlinefan »

Is this a problem with Claude updating code that a human wrote, though? Would Claude do better on code that it started on its own? Humans have a bad tendency to write unmaintainable code (usually at the behest of managers breathing down their necks to HURRY UP even when it doesn't matter). If the code had been designed with good coding practices from the beginning, I wonder if Claude would have struggled so much with it.

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

#345

Post by butterNaN »

nonethewiser wrote: post #256

I dont find this to be indicative of Claude (opus?) at all. My experience doesnt lead me to think it would change a cancel button to blue if I ask it to change an "Add to Cart" button to blue. I assume this is just a contrived example?

This is very close to my experience with Opus 5. Opus 4.6 was the last sane one for me, everything after that seems to have been designed to churn as many tokens as possible, more so with Opus 5

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

#346

Post by jannyfer »

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?

A lot of the more sane people I work with have decided that it's futile to try and have stopped working with Opus (we can't use Fable at work due to data retention policies).

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

#348

Post by herrherrmann »

commandlinefan wrote: post #344

Is this a problem with Claude updating code that a human wrote, though? Would Claude do better on code that it started on its own? Humans have a bad tendency to write unmaintainable code (usually at the behest of managers breathing down their necks to HURRY UP even when it doesn't matter). If the code had been designed with good coding practices from the beginning, I wonder if Claude would have struggled so much with…

That implies that Claude writes better code by default, which isn’t necessarily true. Especially as projects get bigger, you can easily end up with unmaintainable LLM-written code if you don’t actively intervene and know a cleaner way.

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

#349

Post by bmacho »

saghm wrote: post #331
bmacho wrote: post #153

Earlier quoted context omitted.

No. People have an inner monologue, partial results and ideas and they remember that. If they've worked some minutes/hours/weeks on something and you ask them why did they do that, they will either answer honestly and truthfully, lie, or say "I missed that/didn't seem important so I just chose something at random". None of these cases are similar to how AI works.

If you have examples of studies that verify that people are always aware of the gaps in their memories of why they did things rather than their memories sometimes "filling in the blanks", so to speak, I'd be interested. My impression is that the opposite has a lot more evidence in studies (e.g. around the reliability of eyewitness testimony). It's not clear to me whether you're aware of a rigorous basis for your clai…

It's obviously true that when people try to recall memories they either

  1. recall them correctly
  2. say they can't recall them
  3. recall them incorrectly
Are you asking me a study on when people say they remember something (cases 1 and 3) they are usually right or wrong?

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

#350

Post by herrherrmann »

iLoveOncall wrote: post #179
kstenerud wrote: post #34

That's so weird... This doesn't at all match my experience with Claude. I've never seen it behave this way.

This is EXACTLY my experience with it. Ask for it to change one line of code and see it invoke 20 tools and burn 300K tokens before updating the line and adding 50 extra lines of JavaDoc. Only since 4.8 though.

… and run all kinds of scripts to verify the code, ignoring any pre-configured linters.
Post reply on HN