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

331–340 of 448 posts

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

#331

Post by saghm »

bmacho wrote: post #153
taeric wrote: post #119

Earlier quoted context omitted.

I'm growing increasingly confident that this is how people often work, as well.

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 claim or you're just inferring based on what you think makes sense, but I can't help but wonder if it's the later, in which case regardless of the mechanism, the outcome certainly seems to resemble what happens with LLMs.

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

#332

Post by kstenerud »

singularity2001 wrote: post #152
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.

Of course it's not THAT bad, but you can't tell me that you didn't recognize many of the funny turns and twists of the "story". It gets more convincing if you deliberately pick the ambiguous versions.

I never prompt an agent like that, so no.

First thing I do when something goes wrong is tell the agent to stop and diagnose. You can't prompt effectively without three proper information.

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

#333

Post by yonatan8070 »

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…

I've noticed them repeatedly casting the same value to the same type for now reason, like I'd have a Python function with a type-annotated int argument, and inside the function it would cast that int to int, and also at the call site, just in case it wasn't int enough.

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

#334

Post by torginus »

cruffle_duffle wrote: post #300
bahbahbahbah wrote: post #295

Earlier quoted context omitted.

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

"Plus rigorously ensuring backwards compatibility for a project that is 2 hours old and has zero users." That is exactly how the slop accretes and you get a pile of crap. Claude somehow assumes that said 2 hour old userless app is some dusty enterprise app with millions of users and billions of dollars at stake for a 1 second outage. I have to constantly have these things "take a deep breath, step back and look at th…

Which, again, if you attempt to use these LLMs in an actual enterprise project with the assorted legacy mess in it, that does have to have backwards compatiblity, and interacts with 'weird' tech (well, weird to full stack Node/React devs), well it's an exercise in frustration.

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

#335

Post by torginus »

mrinterweb wrote: post #190
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…

> triggered memories Yeah of 10 minutes ago. It is shocking how long some seemingly simple things can take. I know there are some things I can do faster than the LLM and some things it can do faster than me. The amount of rambling BS is the exhausting part.

> Yeah of 10 minutes ago. It is shocking how long some seemingly simple things can take.

And shocking how little code end effort some things take if done by hand.

I am not some hardline LLM hater, just venting my frustration.

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

#336

Post by JeremyNT »

tarxzvf wrote: post #112
_fat_santa wrote: post #84

At least with Codex, this has not been my experience at all. It still screws up sure, but in every case I can ask "why did you do this" and it can trace back what made it take that particular decision. Typically it's always that I either didn't specify the problem correctly or made a really dumb mistake (executing the task on the wrong project....did this one yesterday) or it's something within a skill file that inst…

Models hallucinate plausible answers to why they did things. It might be true and it might be complete fiction.

Yes. But although they can't know "why" a specific "wrong" answer was selected, the response is often still informative, and it can highlight real weaknesses in process or code structure that should be addressed anyway.

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

#337

Post by butterNaN »

I wanted to see what the various phrases in the "slot machine" are. Surprised it doesn't have "LOAD BEARING" in there somewhere:

Caveats:

• ONE HONEST CAVEAT

• ONE THING WORTH STATING PRECISELY

• ONE THING WORTH FLAGGING

• WORTH NAMING

• WORTH STATING PLAINLY

• I DON'T WANT TO LEAVE THIS IMPLICIT

• I'D BE DOING YOU A DISSERVICE

• I DON'T WANT TO BURY THIS

• BETTER NOW THAN LATER

• ONE HONEST TRADEOFF

• I DON'T WANT TO PAPER OVER THIS

• ONE SMALL HOUSEKEEPING ITEM

• THE HONEST PART IS SIMPLER

Pushbacks:

• FAIR PUSHBACK

• FAIR HIT

• THAT'S ON ME

• YOU'RE RIGHT ABOUT THAT

• YOU'RE RIGHT

• YOUR INSTINCT IS RIGHT

• FAIR, AND MORE SPECIFIC THAN IT SOUNDS

• RIGHT, FOR A REASON WORTH NAMING

• I'M NOT GOING TO DEFEND THAT

• YOU'RE RIGHT TO PUSH BACK

Reframes:

• LET ME BE PRECISE

• THE SHARPER DISTINCTION

• THE PART THAT MATTERS

• THE USEFUL PART IS NARROWER

• LESS X THAN Y

• VISIBLE ISSUE / UNDERLYING ISSUE

• THOSE ARE DIFFERENT CLAIMS

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

#338

Post by metek »

yonatan8070 wrote: post #333
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…

I've noticed them repeatedly casting the same value to the same type for now reason, like I'd have a Python function with a type-annotated int argument, and inside the function it would cast that int to int, and also at the call site, just in case it wasn't int enough.

Blast radius minimized

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

#339

Post by yonatan8070 »

taeric wrote: post #119
tarxzvf wrote: post #112

Earlier quoted context omitted.

Models hallucinate plausible answers to why they did things. It might be true and it might be complete fiction.

I'm growing increasingly confident that this is how people often work, as well.

AFAIK this really is true. I've seen some videos about patients who had the connecting part between the left and right halves of the brain cut as a (archaic) treatment for epilepsy.

While it did help the epilepsy, their brain was essentially two brains controlling two halves of the body. With one controlling speech. There were experiments where one eye was shown some instruction text, the corresponding hand performed that instruction, and when asked why they dix that action, the speaking half just made up some plausible, yet completely wrong reason, just like an LLM.

Post reply on HN