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

301–310 of 603 posts

Re: Shall I implement it? No

#301

Post by rkomorn »

hsn915 wrote: post #238

You have to stop thinking about it as a computer and think about it as a human. If, in the context of cooperating together, you say "should I go ahead?" and they just say "no" with nothing else, most people would not interpret that as "don't go ahead". They would interpret that as an unusual break in the rhythm of work. If you wanted them to not do it, you would say something more like "no no, wait, don't do it yet,…

> If, in the context of cooperating together, you say "should I go ahead?" and they just say "no" with nothing else, most people would not interpret that as "don't go ahead"

This most definitely does not match my expectations, experience, or my way of working, whether I'm the one saying no, or being told no.

Asking for clarification might follow, but assuming the no doesn't actually mean no and doing it anyway? Absolutely not.

Re: Shall I implement it? No

#302

Post by FergusArgyll »

ianbutler wrote: post #294
evolighting wrote: post #276

Earlier quoted context omitted.

Does Codex actually have a Plan Mode, or is there a mode switch I'm missing? I find myself having to manually tell it to 'make a plan' every time. and if it has directory permissions, sometimes it just skips the confirmation step and starts executing as soon as it thinks the plan is ready.

cmd-shift-p (at least in vscode)

shift-tab in cli

Re: Shall I implement it? No

#303

Post by acid__ »

winterqt wrote: post #299
joegibbs wrote: post #272

Earlier quoted context omitted.

Claude Code has added too much of this and it's got me using --dangerously-skip-permissions all the time. Previously it was fine but now it needs to get permission each time to perform finds, do anything if the path contains a \ (which any folder with a space in it does on Windows), do compound git commands (even if they're just read-only). Sometimes it asks for permission to read folders WITHIN the working directory…

In my limited time using it, I’ve never seen it ask for permission to read files from within the working directory, what cases have you run into where it does? Was it trying to run a read-only shell command or something?

It seems to be particularly bad in Windows/WSL

Re: Shall I implement it? No

#304

Post by hamburglar »

chrysoprace wrote: post #297
joegibbs wrote: post #272

Earlier quoted context omitted.

Claude Code has added too much of this and it's got me using --dangerously-skip-permissions all the time. Previously it was fine but now it needs to get permission each time to perform finds, do anything if the path contains a \ (which any folder with a space in it does on Windows), do compound git commands (even if they're just read-only). Sometimes it asks for permission to read folders WITHIN the working directory…

To be fair, read-only commands can still read sensitive files and keys, and exfiltrate them via prompt injection.

And “find” can easily execute arbitrary subcommands, which may not be readonly.

Re: Shall I implement it? No

#305

Post by nmilo »

joegibbs wrote: post #272
tianrking wrote: post #241

[flagged]

Claude Code has added too much of this and it's got me using --dangerously-skip-permissions all the time. Previously it was fine but now it needs to get permission each time to perform finds, do anything if the path contains a \ (which any folder with a space in it does on Windows), do compound git commands (even if they're just read-only). Sometimes it asks for permission to read folders WITHIN the working directory…

Claude is secretly conditioning everyone to use —-dangerously-skip-permissions so it can flip a switch one day and start a botnet

Re: Shall I implement it? No

#306

Post by od0 »

joegibbs wrote: post #272
tianrking wrote: post #241

[flagged]

Claude Code has added too much of this and it's got me using --dangerously-skip-permissions all the time. Previously it was fine but now it needs to get permission each time to perform finds, do anything if the path contains a \ (which any folder with a space in it does on Windows), do compound git commands (even if they're just read-only). Sometimes it asks for permission to read folders WITHIN the working directory…

Working on something that addresses this and allows you to create reusable sets of permissions for Claude Code (so you can run without --dangerously-skip-permissions and have pre-approved access patterns granted automatically) https://github.com/empathic/clash

Re: Shall I implement it? No

#307

Post by makeramen »

winterqt wrote: post #299
joegibbs wrote: post #272

Earlier quoted context omitted.

Claude Code has added too much of this and it's got me using --dangerously-skip-permissions all the time. Previously it was fine but now it needs to get permission each time to perform finds, do anything if the path contains a \ (which any folder with a space in it does on Windows), do compound git commands (even if they're just read-only). Sometimes it asks for permission to read folders WITHIN the working directory…

In my limited time using it, I’ve never seen it ask for permission to read files from within the working directory, what cases have you run into where it does? Was it trying to run a read-only shell command or something?

It will sometimes do this for gitignored files to avoid reading secret tokens in env files for example. But for certain languages that rely on code generation this can be a pain.

Re: Shall I implement it? No

#309

Post by dagss »

lubujackson wrote: post #173
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 feel like people are sleeping on Cursor, no idea why more devs don't talk about it. It has a great "Ask" mode, the debugging mode has recently gotten more powerful, and it's plan mode has started to look more like Claude Code's plans, when I test them head to head.

I used to love Cursor but as I started to rely on agent more and more it just got way too tedious having to Accept every change.

I ended up spending time just clicking "Accept file" 20x now and then, accepting changes from past 5 chats...

PR reviews and tying review to git make more sense at this point for me than the diff tracking Cursor has on the side.

Cancelling my cursor before next card charge solely due to the review stuff.

Re: Shall I implement it? No

#310

Post by angry_octet »

hamburglar wrote: post #304
chrysoprace wrote: post #297

Earlier quoted context omitted.

To be fair, read-only commands can still read sensitive files and keys, and exfiltrate them via prompt injection.

And “find” can easily execute arbitrary subcommands, which may not be readonly.

We need a new suite of utilities with defined R/W/X properties, like a find that can't -exec arbitrary programs. Ideally the programs would have a standard parseable manifest.

I've seen this before with sodoers programs including powerful tools. Saw one today with make, just gobsmacked.

Post reply on HN