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

Shall I implement it? No

gist.github.com

Post reply on HN
Print view View original

221–230 of 603 posts

Re: Shall I implement it? No

#221

Post by thomasfromcdnjs »

darkoob12 wrote: post #161
inerte wrote: post #144

Codex has always been better at following agents.md and prompts more, but I would say in the last 3 months both Claude Code got worse (freestyling like we see here) and Codex got EVEN more strict. 80% of the time I ask Claude Code a question, it kinda assumes I am asking because I disagree with something it said, then acts on a supposition. I've resorted to append things like "THIS IS JUST A QUESTION. DO NOT EDIT COD…

This is not Claude Code. And my experience is the opposite. For me Codex is not working at all to the point that it's not better than asking the chat bot in the browser.

A lot of people dunking but as this comment says, it is not claude code. (just opus 4.6)

Re: Shall I implement it? No

#222

Post by clbrmbr »

al_borland wrote: post #177
bluefirebrand wrote: post #41

Earlier quoted context omitted.

This is really just how the tech industry works. We have abused the concept of consent into an absolute mess My personal favorite way they do this lately is notification banners for like... Registering for news letters "Would you like to sign up for our newsletter? Yes | Maybe Later" Maybe later being the only negative answer shows a pretty strong lack of understanding about consent!

Worse yet, instead of a checkbox to opt in/out of a newsletter or marketing email when signing up or checking out, it simply opts the user in. Simply doing business with a company is consent to spam, with the excuse that the user can unsubscribe if they don’t want it. Tactics like these should be illegal, but instead they have become industry standards.

Not everyone. If your business is chill and you are REEEEALY thoughtful and respectful with newsletters you will be rewarded with open rates well in excess of 50%…

Re: Shall I implement it? No

#223

Post by silentkat »

dostick wrote: post #213

Its gotten so bad that Claude will pretend in 10 of 10 cases that task is done/on screenshot bug is fixed, it will even output screenshot in chat, and you can see the bug is not fixed pretty clear there. I consulted Claude chat and it admitted this as a major problem with Claude these days, and suggested that I should ask what are the coordinates of UI controls are on screenshot thus forcing it to look. So I did that…

Oh, no, I had these grand plans to avoid this issue. I had been running into it happening with various low-effort lifts, but now I'm worried that it will stay a problem.

Re: Shall I implement it? No

#224

Post by skeeter2020 »

AnotherGoodName wrote: post #178
stavros wrote: post #171

Earlier quoted context omitted.

I've added an instruction: "do not implement anything unless the user approves the plan using the exact word 'approved'". This has fixed all of this, it waits until I explicitly approve.

There’s an extension to this problem which I haven’t got past. More generally I’d like the agent to stop and ask questions when it encounters ambiguity that it can’t reasonably resolve itself. If someone can get agents doing this well it’d be a massive improvement (and also solve the above).

what gung-ho, talented-but-naive junior developer has ever done that?

Re: Shall I implement it? No

#225

Post by clbrmbr »

bushido wrote: post #197

The "Shall I implement it" behavior can go really really wrong with agent teams. If you forget to tell a team who the builder is going to be and forget to give them a workflow on how they should proceed, what can often happen is the team members will ask if they can implement it, they will give each other confirmations, and they start editing code over each other. Hilarious to watch, but also so frustrating. aside: I…

Huh. I’m missing out I guess. Is there a plugin you use for spinning them up? Heavy superpowers/CC user here.

Re: Shall I implement it? No

#226

Post by gambiting »

dostick wrote: post #213

Its gotten so bad that Claude will pretend in 10 of 10 cases that task is done/on screenshot bug is fixed, it will even output screenshot in chat, and you can see the bug is not fixed pretty clear there. I consulted Claude chat and it admitted this as a major problem with Claude these days, and suggested that I should ask what are the coordinates of UI controls are on screenshot thus forcing it to look. So I did that…

>>It’s like 95% of development is web and LLM providers care only about that.

I've been trying to use it for C++ development and it's maybe not completely useless, but it's like a junior who very confidently spouts C++ keywords in every conversation without knowing what they actually mean. I see that people build their entire companies around it, and it must be just web stuff, right? Claude just doesn't work for C++ development outside of most trivial stuff in my experience.

Re: Shall I implement it? No

#227

Post by clbrmbr »

breton wrote: post #63
serf wrote: post #27

Earlier quoted context omitted.

never trust a screenshot of a command prompts output blindly either. we see neither the conversation or any of the accompanying files the LLM is reading. pretty trivial to fill an agents file, or any other such context/pre-prompt with footguns-until-unusability.

You are welcome to review the full session here - https://gist.github.com/bretonium/d1672688feb5c5cbccf894c92d...

Do you have a more detailed trace that shows the system reminders? Do you know in which order it was fed into the LLM call that resulted in the bad reasoning?

Re: Shall I implement it? No

#228

Post by TZubiri »

I want to clarify a little bit about what's going on.

Codex (the app, not the model) has a built in toggle mode "Build"/"Plan", of course this is just read-only and read-write mode, which occurs programatically out of band, not as some tokenized instruction in the LLM inference step.

So what happened here was that the setting was in Build, which had write-permissions. So it conflated having write permissions with needing to use them.

Re: Shall I implement it? No

#229

Post by Leynos »

steelbrain wrote: post #220
dostick wrote: post #213

Its gotten so bad that Claude will pretend in 10 of 10 cases that task is done/on screenshot bug is fixed, it will even output screenshot in chat, and you can see the bug is not fixed pretty clear there. I consulted Claude chat and it admitted this as a major problem with Claude these days, and suggested that I should ask what are the coordinates of UI controls are on screenshot thus forcing it to look. So I did that…

> And on top of it, if you develop for native macOS, There’s no official tooling for visual verification. It’s like 95% of development is web and LLM providers care only about that. Thinking out loud here, but you could make an application that's always running, always has screen sharing permissions, then exposes a lightweight HTTP endpoint on 127.0.0.1 that when read from, gives the latest frame to your agent as a P…

https://github.com/steipete/Peekaboo

Re: Shall I implement it? No

#230

Post by VortexLain »

gambiting wrote: post #226
dostick wrote: post #213

Its gotten so bad that Claude will pretend in 10 of 10 cases that task is done/on screenshot bug is fixed, it will even output screenshot in chat, and you can see the bug is not fixed pretty clear there. I consulted Claude chat and it admitted this as a major problem with Claude these days, and suggested that I should ask what are the coordinates of UI controls are on screenshot thus forcing it to look. So I did that…

>>It’s like 95% of development is web and LLM providers care only about that. I've been trying to use it for C++ development and it's maybe not completely useless, but it's like a junior who very confidently spouts C++ keywords in every conversation without knowing what they actually mean. I see that people build their entire companies around it, and it must be just web stuff, right? Claude just doesn't work for C++…

GPT models are generally much better at C++, although they sometimes tend to produce correct but overengineered code, and the operator has to keep an eye on that.
Post reply on HN