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

511–520 of 603 posts

Re: Shall I implement it? No

#511

Post by Sharlin »

what wrote: post #426
jkaplowitz wrote: post #236

Earlier quoted context omitted.

At least if this "Store cookies?" question is implicitly referencing EU regulations, those regulations don't require consent for cookies which are considered essential, including a cookie to store the response to the consent question (but certainly not advertising tracking cookies). So the respectful replacement for "Ask me again" is "Essential cookies only" (or some equivalent wording to "Essential" like "Required"…

I’ve not seen a site that remembers your selection of “reject all”/“essential only”. It would actually be hard to argue that it would count as an essential cookie, nothing about the site depends on remembering your rejection. I guess that makes “maybe later” more reasonable since it’s going to ask you every time until you relent.

Huh? Of course those get remembered, and of course it's allowed by GDPR. If the websites you visit don't remember "reject all", they're doing it maliciously (or out of incompetence, I guess).

Re: Shall I implement it? No

#512

Post by girvo »

windward wrote: post #508
aidos wrote: post #500

Earlier quoted context omitted.

One annoying thing about that flow is that when you change the world outside the model it breaks its assumptions and it loses its way faster (in my experience).

And accuses you of being a linter

To be fair to the model, I really can act like one sometimes.

Re: Shall I implement it? No

#516

Post by mlrtime »

user3939382 wrote: post #427
deaux wrote: post #300

Earlier quoted context omitted.

> 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 If 3 years into LLMs even HNers still don't understand that the response they give to this kind of question is completely meaningless, the average person really doesn't stand a chance.

It’s not meaningless. It’s a signal that the agent has run out of context to work on the problem which is not something it can resolve on its own. Decomposing problems and managing cognitive (or quasi cognitive in this case) burden is a programmer’s job regardless of the particular tools.

I think you are saying what I was about to suggest:

For this single problem, open a new claude session with this particular issue and refining until fixed, then incorporating it into the larger project.

I think the QA agent might have been the same step here, but it depends on how that QA agent was setup.

Re: Shall I implement it? No

#517

Post by sumeno »

iainmck29 wrote: post #509
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…

I find this thread surprising honestly. Claude Code is my daily driver and I consider myself a real power user. If you have your commands/agents/skills set up correctly you should never be running into these issues

Ahh, "you're holding it wrong"

The classics never go out of style

Re: Shall I implement it? No

#518

Post by bdangubic »

smackeyacky wrote: post #456
bdangubic wrote: post #385

Earlier quoted context omitted.

This - per extensive experiments - works about as well as when I tell my wife to calm down

Asking might work better than telling

How do you do that???? Say the words but in the form of a question? I feel like that will go a lot worse than just telling (but nicely). I have a daughter too so I am genuinely willing to try anything

Re: Shall I implement it? No

#519

Post by jurgenburgen »

sroussey wrote: post #208
bushido wrote: post #181

Earlier quoted context omitted.

Cursor implemented something a while back where it started acting like how ChatGPT does when it's in its auto mode. Essentially, choosing when it was going to use what model/reasoning effort on its own regardless of my preferences. Basically moved to dumber models while writing code in between things, producing some really bad results for me. Anecdotal, but the reason I will never talk about Cursor is because I will…

Don’t use the “auto” model and you will be fine. You just described their “auto” behavior, which I’m guessing uses grok. Using it with specific models is great, though you can tell that Anthropic is subsidizing Claude Code as you watch your API costs more directly. Some day the subsidy will end. Enjoy it now! And cursor debugging is 10x better, oh my god. I have switched to 70% Claude Code, 10% Copilot code reviews (…

> get four to implement the same thing at the same time, then review their choices

Why would you do that to yourself? Reviewing 4 different solutions instead of 1 is 4 times the amount of work.

Re: Shall I implement it? No

#520

Post by orphea »

miki123211 wrote: post #493
torben-friis wrote: post #156

Earlier quoted context omitted.

>I've resorted to append things like "THIS IS JUST A QUESTION. DO NOT EDIT CODE. DO NOT RUN COMMANDS". Which is ridiculous. Funny to read that, because for me it's not even new behavior. I have developed a tendency to add something like "(genuinely asking, do not take as a criticism)". I'm from a more confrontational culture, so I just assumed this was just corporate American tone framing criticism softly, and me com…

I just append "explain", or start with "tell me." So instead of: "Why is foo str|None and not str" I'd do: "tell me why foo is str|None and not str" or "Why is foo str|None and not str, explain" Which is usually good enough. If you're asking this kind of question, the answer probably deserves to be a code comment.

  > the answer probably deserves to be a code comment.
No..? As others mentioned, somehow Codex is "smart" enough to tell questions and requests apart.
Post reply on HN