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

331–340 of 603 posts

Re: Shall I implement it? No

#331

Post by motoboi »

adriand wrote: post #319
motoboi wrote: post #315

Earlier quoted context omitted.

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 s…

I insist on the text generator nature of the thing. It’s just that we built harnesses to activate on certain sequences of text.

Think of it as three people in a room. One (the director), says: you, with the red shirt, you are now a plane copilot. You, with the blue shirt, you are now the captain. You are about to take off from New York to Honolulu. Action.

Red: Fuel checked, captain. Want me to start the engines?

Blue: yes please, let’s follow the procedure. Engines at 80%.

Red: I’m executing: raise the levers to 80%

Director: levers raised.

Red: I’m executing: read engine stats meters.

Director: Stats read engine ok, thrust ok, accelerating to V0.

Now pretend the director, when heard “I’m executing: raise the levers to 80%”, instead of roleplaying, she actually issue a command to raise the engine levers of a plane to 80%. When she hears “I’m executing: read engine stats”, she actually get data from the plane and provide to the actor.

See how text generation for a role play can actually be used to act on the world?

In this mind experiment, the human is the blue shirt, Opus 4-6 is the red and Claude code is the director.

Re: Shall I implement it? No

#332

Post by jazzyjackson »

ryoshu wrote: post #330
tianrking wrote: post #241

[flagged]

Do not enforce invariants with an LLM. Do not enforce invariants with an LLM. Do not enforce invariants with an LLM. Do not enforce invariants with an LLM.

Thou shalt not make repetitive generic music,

thou shalt not make repetitive generic music,

thou shalt not make repetitive generic music,

thou shalt not make repetitive generic music.

Thou shalt not pimp my ride.

Thou shalt not scream if you wanna go faster.

Thou shalt not move to the sound of the wickedness.

Thou shalt not make some noise for Detroit.

When I say "Hey" thou shalt not say "Ho".

When I say "Hip" thou shalt not say "Hop".

When I say, he say, she say, we say, make some noise - kill me.

- Dan le Sac vs Scroobius Pip

Re: Shall I implement it? No

#333

Post by jazzyjackson »

JeremyNT wrote: post #326
raincole wrote: post #313

Earlier quoted context omitted.

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.

Yep, it's easier to ask forgiveness than permission. It's far easier to undo the 1% of the time they fuck up in a serious way than it is to manually audit and allow an the routine stuff. The key is to only give them access to things you're willing to lose. This is also why giving them any kind of direct write access to production is a bad idea.

Talk about code smell

If you arent manually auditing, you only notice the fuck ups when they’re instantaneous

If you don’t trust it to interact with prod, but still trust it to write code that will run on prod… you’re still trusting it with write access to prod.

The only thing I’m willing to let Claude write for me is a static site generator, because static files without JS aren’t going to do any damage, it either loads or it doesn’t.

Re: Shall I implement it? No

#335

Post by genidoi »

mildred593 wrote: post #15

Never trust a LLM for anything you care about.

Especially given the LLM does not trust the user. An LLM can be jailbroken into lowering it's guardrails, but no amount of rapport building allows you to directly talk about material details of banned topics. Might as well never trust it.

Re: Shall I implement it? No

#336

Post by saint_yossarian »

BosunoB wrote: post #190
alpaca128 wrote: post #184

Earlier quoted context omitted.

> it's aware that you could've just not responded It's not aware of anything and doesn't know that a world outside the context window exists.

No, it has knowledge of what it is and how it is used. I'm guessing you and the other guy are taking issue with the words "aware of" when I'm just saying it has knowledge of these things. Awareness doesn't have to imply a continual conscious state.

I think to many people awareness does imply consciousness, i.e. the thing that is aware of the knowledge.

Re: Shall I implement it? No

#337

Post by raw_anon_1111 »

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 see nothing wrong with that. If I “fuck up big time” before AI, I would just git restore. There is absolutely nothing on my work computer or personal computer that I couldn’t just throw it in the ocean and within a half a day have everything restored to just like it was - including the data.

Re: Shall I implement it? No

#338

Post by redman25 »

shitloadofbooks wrote: post #191
hungryhobbit wrote: post #159

Earlier quoted context omitted.

[flagged]

I certainly wouldn't use a compiler that "screws up" 1% of the time; that's the perfect amount where it's extremely common where everything I use it for will have major issues but also so laborious to find amongst the 99% of correct output that I might as well not use it in the first place. Which is ironically, the exact case those of us who don't find LLM-assisted coding "worth it" make.

How about a human coworker who screws up 1% of the time? Doesn’t sound so bad in that light. It’s the nature of being human.

Good code review is the solution but if it’s faster to do it yourself, that’s fine too.

Re: Shall I implement it? No

#339

Post by raw_anon_1111 »

jazzyjackson wrote: post #333
JeremyNT wrote: post #326

Earlier quoted context omitted.

Yep, it's easier to ask forgiveness than permission. It's far easier to undo the 1% of the time they fuck up in a serious way than it is to manually audit and allow an the routine stuff. The key is to only give them access to things you're willing to lose. This is also why giving them any kind of direct write access to production is a bad idea.

Talk about code smell If you arent manually auditing, you only notice the fuck ups when they’re instantaneous If you don’t trust it to interact with prod, but still trust it to write code that will run on prod… you’re still trusting it with write access to prod. The only thing I’m willing to let Claude write for me is a static site generator, because static files without JS aren’t going to do any damage, it either lo…

If you are a team lead or above, do you manually audit every line of code that other developers on your team write even when you are the one that will ultimately be held responsible? Every library you use?

Re: Shall I implement it? No

#340

Post by connorbrinton »

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…

I've found Claude Code's built-in sandbox to strike a good balance between safety and autonomy on macOS. I think it's available on Windows via WSL2 (if you're looking for a middle ground between approving everything manually and --dangerously-skip-permissions)
Post reply on HN