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

311–320 of 603 posts

Re: Shall I implement it? No

#311

Post by muyuu »

ddoolin wrote: post #169
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…

Same here. I quickly learned that if you merely ask questions about it's understanding or plans, it starts looking for alternatives because my questioning is interpreted as rejection or criticism, rather than just taking the question at face value. So I often (not always) have to caveat questions like that too. It's really been like that since before Claude Code or Codex even rolled around. It's just strange because…

Do what you would do with a person, which is to allocate time for them to produce documentation, and be specific about it.

Re: Shall I implement it? No

#313

Post by raincole »

tianrking wrote: post #241

[flagged]

Everyone who uses these tools seriously is running it on YOLO mode. It might sound crazy for someone who just started adopting agentic coding but it's how things are done now. Either that or just hand coding.

The SOTA of permission management is just to git restore when AI fucks up, and to roll back docker snapshot when it fucks up big time.

Re: Shall I implement it? No

#314

Post by andoando »

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…

Yeah I don't know why they didn't figure to have something in between. I find it completely unusable without the flag.

Even a --permit-reads would help a lot

Re: Shall I implement it? No

#315

Post by motoboi »

deaux wrote: post #300
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…

> 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.

The whole “chat with an AI” paradigm is the culprit here. Priming people to think they are actually having a conversation with something that has a mind model.

It’s just a text generator that generates plausible text for this role play. But the chat paradigm is pretty useful in helping the human. It’s like chat is a natural I/O interface for us.

Re: Shall I implement it? No

#316

Post by andoando »

raincole wrote: post #313
tianrking wrote: post #241

[flagged]

Everyone who uses these tools seriously is running it on YOLO mode. It might sound crazy for someone who just started adopting agentic coding but it's how things are done now. Either that or just hand coding. The SOTA of permission management is just to git restore when AI fucks up, and to roll back docker snapshot when it fucks up big time.

I ran thousands of prompts by now and at most the only issue I had is it deleting code it wrote, which has been easy to recover

Re: Shall I implement it? No

#317

Post by dullcrisp »

vidarh wrote: post #118
sid_talks wrote: post #38

[flagged]

I've spent 30 years seeing the junk many human developers deliver, so I've had 30 years to figure out how we build systems around teams to make broken output coalesce into something reliable. A lot of people just don't realise how bad the output of the average developer is, nor how many teams successfully ship with developers below average. To me, that's a large part of why I'm happy to use LLMs extensively. Some thi…

I’m sorry.

Re: Shall I implement it? No

#318

Post by steelbrain »

Leynos wrote: post #229
steelbrain wrote: post #220

Earlier quoted context omitted.

> 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

I didnt realize how prolific the OpenClaw author was. Thanks for sharing!

Re: Shall I implement it? No

#319

Post by adriand »

motoboi wrote: post #315
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.

The whole “chat with an AI” paradigm is the culprit here. Priming people to think they are actually having a conversation with something that has a mind model. It’s just a text generator that generates plausible text for this role play. But the chat paradigm is pretty useful in helping the human. It’s like chat is a natural I/O interface for us.

I disagree that it’s “just a text generator” but you are so right about how primed people are to think they’re talking to a person. One of my clients has gone all-in on openclaw: my god, the misunderstanding is profound. When I pointed out a particularly serious risk he’d opened up, he said, “it won’t do that, because I programmed it not to”. No, you tried to persuade it not to with a single instruction buried in a swamp of markdown files that the agent is itself changing!

Re: Shall I implement it? No

#320

Post by angry_octet »

6thbit wrote: post #274
tianrking wrote: post #241

[flagged]

Is this understanding correct: The LLM uses harness tools to ask for permission, then interprets the answer and proceeds. If so, this can't live 100% on the harness. First because you would need the harness to decide when the model should ask for permission or not which is more of an llm-y thing to do. The harness can prevent command executions but wouldn't prevent this case where model goes off and begins reading fi…

Harness needs to intercept all too calls and compare with an authorisation list. The problem is that this is using already granted core permissions.

So you have to have a tighter set of default scopes, which means approving a whole batch of tool calls, at the harness layer not as chat. This is obviously more tedious.

The answer might be another tool that analyses the tool calls and presents a diagram of list of what would be fetched, sent, read and written. But it would get very hard to truly observe what happens when you have a bunch of POST calls.

So maybe it needs a kind of incremental approval, almost like a series of mini-PRs for each change.

Post reply on HN