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

PS3 Emulator Devs Politely Ask That People Stop Flooding It with AI PRs

kotaku.com

Post reply on HN
Print view View original

121–130 of 162 posts

Re: PS3 Emulator Devs Politely Ask That People Stop Flooding It with AI PRs

#121

Post by saagarjha »

loloquwowndueo wrote: post #4
saagarjha wrote: post #2

The emulation space is particularly bad about this because there are a lot of semi-technical and "well meaning" users who will do anything to get their games to play better and AI gives them a way to make it seem like they are doing something useful, without being able to judge the quality of the output they are producing. One of the projects I work on recently had a guy drop by and explain that he wanted to use Clau…

A good argument to use could be: I can use Claude myself, so I will if I need to, but you using Claude on my behalf doesn’t save me any work, it just introduces another layer of noise into the mix. (Yes calling the guy “noise” haha)

Yeah I basically said this and the guy claimed I didn't understand what he was offering

Re: PS3 Emulator Devs Politely Ask That People Stop Flooding It with AI PRs

#122

Post by saagarjha »

NoMoreNicksLeft wrote: post #27
saagarjha wrote: post #2

The emulation space is particularly bad about this because there are a lot of semi-technical and "well meaning" users who will do anything to get their games to play better and AI gives them a way to make it seem like they are doing something useful, without being able to judge the quality of the output they are producing. One of the projects I work on recently had a guy drop by and explain that he wanted to use Clau…

Over the last month, I've been using Claude to assist in some things that were at the edge of my ability (or maybe just a hair's breadth beyond it). I've added features to open source projects that everyone's been waiting years for. I always fork it telling myself that I want to be able to submit PRs, but really I'm just making the changes for myself, since I don't even have the nerve to show it off. If these people…

There's another person who for a long time wrote kind of hacky patches to work around bugs (e.g. disabling multithreading to avoid a longstanding race) and now he's using AI to fix everything in his own fork. I guess he can do that? We haven't really been able to use any of his changes though.

Re: PS3 Emulator Devs Politely Ask That People Stop Flooding It with AI PRs

#123

Post by drw85 »

onion2k wrote: post #88
heavyset_go wrote: post #75

Earlier quoted context omitted.

No, it is a tooling problem. The tooling is telling laymen that they built wonderful things that definitely work and perfectly fix and add features. The tooling gasses them up and is simply wrong in these cases. If your tool regularly lies, gaslights and produces wrong results, that's a tooling issue.

If your tool regularly lies, gaslights and produces wrong results, that's a tooling issue. It's a human issue if you don't recognise that the code it's generated is wrong. That will never change no matter how good the tooling gets.

Would it be a human issue, if you type something into a calculator and the calculated result is wrong?

Would anyone use a calculator confidently, if the result was randomly generated?

Re: PS3 Emulator Devs Politely Ask That People Stop Flooding It with AI PRs

#124

Post by gambiting »

HDBaseT wrote: post #3

I recently just started using Claude/ChatGPT/China models for some PS3 homebrew work. Every model seemingly falls flat in this scope of programming. The PS3 is very complex and the tooling is fairly undocumented in a lot of instances. It doesn't surprise me most of these AI PR's are nonsense. If anyone else has attempted writing PS3 homebrew apps using AI and has refined their tooling/systems/automation please let me…

I don't know about homebrew(not done it since PSP times), but I work in games development and we use Claude extensively. The trick is just to feed it all the console docs and then it's pretty amazing. If you have access to PS3 docs still, just give them to Claude as part of the session, I'm sure it will improve tenfold.

Re: PS3 Emulator Devs Politely Ask That People Stop Flooding It with AI PRs

#125

Post by CWwdcdk7h »

villgax wrote: post #72

Just paywall it, pays for development, queue prioritization and in return they get code merged into a popular project and visibility

Isn't it simpler, in general, to just move the development off GitHub, while leaving existing repo in sync, so it can harmlessly drown in PRs from people who didn't bother to even read project contribution guidelines?

Re: PS3 Emulator Devs Politely Ask That People Stop Flooding It with AI PRs

#126

Post by leidenfrost »

mvid wrote: post #112
walletdrainer wrote: post #100

Earlier quoted context omitted.

If someone believes a hammer when it tells them such things, they should probably have some sort of a caretaker assigned to help them through life.

If hammer companies were suddenly the most valuable international companies, and spent millions on ad campaigns and lobbying about trusting the hammer interface, then you can assume a large amount of people might trust the hammer interface

Still, it's a tool.

Even if your tool learns to talk and to make decisions, it's still a tool, not a person. You're the person and the one responsible for the decisions you make based on your tools.

Going back from the analogy, the problem is that we conflated software with "coders". A lot of people thought their job was to create code, we gave them a tool to generate a lot of code fast, and they truly think that "more code" = "more good"

Re: PS3 Emulator Devs Politely Ask That People Stop Flooding It with AI PRs

#127

Post by digitalPhonix »

perching_aix wrote: post #102
Den_VR wrote: post #87

Earlier quoted context omitted.

Does the hammer lie to you that everything is a nail? Can a voltmeter _lie_ to you? EE are expected to know when their measurements are wrong. And Professional Engineers are legally accountable for consequences of such mistakes.

> Can a voltmeter _lie_ to you? Hell fucking yes it can?

When used according to it’s datasheet/user manual, how?

Re: PS3 Emulator Devs Politely Ask That People Stop Flooding It with AI PRs

#128

Post by digitalPhonix »

possibleworlds wrote: post #91
Den_VR wrote: post #87

Earlier quoted context omitted.

Does the hammer lie to you that everything is a nail? Can a voltmeter _lie_ to you? EE are expected to know when their measurements are wrong. And Professional Engineers are legally accountable for consequences of such mistakes.

If a hammer had a chat interface that said everything was a nail then the answer would be yes, the hammer lies to you about everything being a nail.

That wasn’t the question though? A hammer doesn’t have a chat interface, that’s the point.

Re: PS3 Emulator Devs Politely Ask That People Stop Flooding It with AI PRs

#129

Post by digitalPhonix »

heavyset_go wrote: post #118
Den_VR wrote: post #87

Earlier quoted context omitted.

Does the hammer lie to you that everything is a nail? Can a voltmeter _lie_ to you? EE are expected to know when their measurements are wrong. And Professional Engineers are legally accountable for consequences of such mistakes.

If I had a hammer robot that I told to go hammer some nails in a birdhouse and it goes "Sure, I'm on it!" then it nails a cat to the wall and says "Here's you new complete birdhouse, it's perfect in everyway and will make everyone jealous", then yes, that is a tooling issue.

The question wasn’t about a hammer robot, it was about a hammer

Re: PS3 Emulator Devs Politely Ask That People Stop Flooding It with AI PRs

#130

Post by perching_aix »

digitalPhonix wrote: post #127
perching_aix wrote: post #102

Earlier quoted context omitted.

> Can a voltmeter _lie_ to you? Hell fucking yes it can?

When used according to it’s datasheet/user manual, how?

When their precision mismatches their accuracy (or your expectations as driven by their design), just like with any other metrology tool.

Now you might say: "but the datasheet will give you the tolerances, and the manual will tell you to mind it!"

And yes, that's true. Just like how LLM providers also do: they tell you that outputs may be arbitrarily wrong, and that you should always check for mistakes.

Is this bullshit? Yes. So are metrology tools that have a mismatching precision and accuracy, need calibration, and have designs that fail to make you mind either of these, sending you to reading duty instead. Which just so happens to be a whole lot of them.

It is also absolutely not bullshit of course, because it is a fundamental limitation, just like those properties are for metrology devices. LLMs produce arbitrary natural language. Short of becoming able to perfectly read and predict the users' mind, they'll never be able to make any hard assurances, ever.

Defective devices also exist, and so do incorrect / incomplete documentation.

Post reply on HN