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

FreeBSD doesn't have Wi-Fi driver for my old MacBook, so AI built one for me

vladimir.varank.in

Post reply on HN
Print view View original

131–140 of 397 posts

Re: FreeBSD doesn't have Wi-Fi driver for my old MacBook, so AI built one for me

#131

Post by slopinthebag »

jomohke wrote: post #128
slopinthebag wrote: post #78

> I didn’t write any piece of code there. There are several known issues, which I will task the agent to resolve, eventually. Meanwhile, I strongly advise against using it for anything beyond a studying exercise. Months of effort and three separate tries to get something kind of working but which is buggy and untested and not recommended for anyone to use, but unfortunately some folks will just read the headline and…

You're validly critiquing where it is now. The hype people are excited because they're guessing where it's going. This is notable because it's a milestone that was not previously possible: a driver that works, from someone who spent ~zero effort learning the hardware or driver programming themselves. It's not production ready, but neither is the first working version of anything. Do you see any reason that progress w…

> Do you see any reason progress will stop abruptly here?

Yeah, money and energy. And fundamental limitations of LLM's. I mean, I'm obviously guessing as well because I'm not an expert, but it's a view shared by some of the biggest experts in the field ¯\_(ツ)_/¯

I just don't really buy the idea that we're going to have near-infinite linear or exponential progress until we reach AGI. Reality rarely works like that.

Re: FreeBSD doesn't have Wi-Fi driver for my old MacBook, so AI built one for me

#132

Post by lstodd »

WD-42 wrote: post #44
diath wrote: post #17

Earlier quoted context omitted.

The primary reason why it worked is because Claude could rip off the Linux driver. Without any prior work to rely on, how will the AI figure out proprietary hardware?

He also mentioned it took 2 months. I’m actually wondering how long it would take to do the Linux to BSD port by eyeball, or at least ai assisted. Probably not that much longer? I guess it depends on wall time vs real time.

I estimate two weeks from having never seen kernel source to something reasonably stable based on experience with block devices/raid controllers. But I knew a bit of C (had patches merged into SVN, Exim4, etc).

Re: FreeBSD doesn't have Wi-Fi driver for my old MacBook, so AI built one for me

#133

Post by 1024core »

jomohke wrote: post #128
slopinthebag wrote: post #78

> I didn’t write any piece of code there. There are several known issues, which I will task the agent to resolve, eventually. Meanwhile, I strongly advise against using it for anything beyond a studying exercise. Months of effort and three separate tries to get something kind of working but which is buggy and untested and not recommended for anyone to use, but unfortunately some folks will just read the headline and…

You're validly critiquing where it is now. The hype people are excited because they're guessing where it's going. This is notable because it's a milestone that was not previously possible: a driver that works, from someone who spent ~zero effort learning the hardware or driver programming themselves. It's not production ready, but neither is the first working version of anything. Do you see any reason that progress w…

Not a huge fan of @sama, but he is quoted as saying: this is the worst these models will every be!

Puts all criticism in a new perspective.

Re: FreeBSD doesn't have Wi-Fi driver for my old MacBook, so AI built one for me

#134

Post by SOLAR_FIELDS »

nozzlegear wrote: post #66
SOLAR_FIELDS wrote: post #56

Earlier quoted context omitted.

Given that literally no one is enforcing this it seems like a moral rather than a business decision here no? Isn’t the risk here that your competitors, who have no such moral qualms, are just going to commit all sorts of blatant copyright infringement but it really doesn’t matter because no one is enforcing it?

Who is a competitor for Asahi? What would that even entail? > Given that literally no one is enforcing this Presumably Apple's lawyers would enforce it.

I’ll believe it when I see a court case of them going after someone for some ai generated slop and they win. Don’t see much evidence of that happening right now, or really ever since the advent of these things

Re: FreeBSD doesn't have Wi-Fi driver for my old MacBook, so AI built one for me

#135

Post by cortesoft »

slopinthebag wrote: post #111
petcat wrote: post #107

Earlier quoted context omitted.

I strongly suspect that somebody with domain knowledge around Wi-Fi drivers and OS kernel drivers could prompt the llm to spit out a lot more robust code than this guy was able to. That's not a knock on him, he was just trying to see what he could do. It's impressive what he actually accomplished given how little effort he put forth and how little knowledge he had about the subject.

Someone with domain knowledge could also just write the code instead of trying to get the stochastic prediction machine to generate it. I thought the whole point was to allow people without said expertise to generate it. After all, that seems to be the promise.

> Someone with domain knowledge could also just write the code instead of trying to get the stochastic prediction machine to generate it.

Well, people with the domain knowledge exist, yet they have not yet written this driver... why not?

Because there is other code those experts want to write, and they don't have time to write it all... but what if they could just give a fairly straightforward prompt and have the LLM do it for them? And if it only took minor tweaks to the prompt to have it write drivers for all the myriad combinations of hardware and software? At that point, there might be enough time to write it all.

Just because people exist that can DO all the work doesn't mean we have enough person-hours to do ALL the work.

Re: FreeBSD doesn't have Wi-Fi driver for my old MacBook, so AI built one for me

#136

Post by SOLAR_FIELDS »

Vegenoid wrote: post #108
SOLAR_FIELDS wrote: post #51

Earlier quoted context omitted.

This is also where I think we end up. If the behavior of the system is specified well enough, then the code itself is cheap and throwaway. Why have a static system that is brittle to external changes when you can just reconstruct the system on the fly? Might be quite awhile before you can do this with large systems but we already see this on smaller contextual scales such as Claude Code itself

> If the behavior of the system is specified well enough Then it becomes code: a precise symbolic representation of a process that can be unambiguously interpreted by a computer. If there is ambiguity, then that will be unsuitable for many systems.

The word “many” is carrying a lot of weight here. Given the probabilistic nature of AI I suspect that systems that are 98% correct will be just fine for all but the “this plane will crash” or “this person will get cancer” use cases. If the recreation of the system failed in that 2% by slightly annoying some end user, who gives a shit? If the stakes are low, and indeed they are for a large majority of software use cases, probabilistic approximation of everyone’s open source will do just fine.

If you’re worried about them achieving the 98%, worry no more, due to the probabilistic nature it will eventually converge on 9’s. Just keep sending the system through the probabilistic machine until it reaches your desired level of nines

Re: FreeBSD doesn't have Wi-Fi driver for my old MacBook, so AI built one for me

#137

Post by ssl-3 »

calmbonsai wrote: post #28
rvz wrote: post #7

Earlier quoted context omitted.

> We're very close to just being about to set an AI coding agent to brute-force a driver for anything. That sounds quite naive and it isn't that simple. Even the author expressed caution and isn't sure about how robust the driver is since he hasn't seen the code himself nor does he know if it works reliably. Even entertaining the idea, someone would have already have replaced those closed source Nvidia drivers that h…

> We're very close to just being about to set an AI coding agent to brute-force a driver for anything. This is false. To "brute force" a driver, you'd need a feedback loop between the hardware's output and the driver's input. While, in theory, this is possible for some analog-digital traducers (e.g WI-FI radio), if the hardware is a human-interface system (joystick, monitor, mouse, speaker, etc.) you literally need a…

Strictly speaking, I don't think we need a human to run repetitive tests. We just need the human to help with the physical parts of the testing jig.

For instance: A microphone (optionally: a calibrated microphone; extra-optionally: in an isolated anechoic chamber) is a simple way to get feedback back into the machine about the performance of a speaker. (Or, you know: Just use a 50-cent audio transformer and electrically feed the output of the amplifier portion of the [presumably active] speaker back into the machine in acoustic silence.)

And I don't have to stray too far into the world of imagination to notice that the hairy, custom Cartesian printer in the corner of the workshop quite clearly resembles a machine that can move a mouse over a surface in rather precise ways. (The worst that can happen is probably not as bad as many of us have seen when using printers in their intended way, since at least there's no heaters and molten plastic required. So what if it disassembles itself? That's nothing new.)

Whatever the testing jig consists of, the bot can write the software part of the tests, and the tests can run as repetitiously as they need to.

Re: FreeBSD doesn't have Wi-Fi driver for my old MacBook, so AI built one for me

#138

Post by snowhale »

Vegenoid wrote: post #114
snowhale wrote: post #64

Earlier quoted context omitted.

[dead]

You haven't addressed the parent's concern at all, which is that what the LLM was trained on, not what was fed into its context window. The Linux driver is almost certainly in the LLM's training data. Also, the "spec" that the LLM wrote to simulate the "clean-room" technique is full of C code from the Linux driver.

[dead]

Re: FreeBSD doesn't have Wi-Fi driver for my old MacBook, so AI built one for me

#140

Post by selridge »

slopinthebag wrote: post #131
jomohke wrote: post #128

Earlier quoted context omitted.

You're validly critiquing where it is now. The hype people are excited because they're guessing where it's going. This is notable because it's a milestone that was not previously possible: a driver that works, from someone who spent ~zero effort learning the hardware or driver programming themselves. It's not production ready, but neither is the first working version of anything. Do you see any reason that progress w…

> Do you see any reason progress will stop abruptly here? Yeah, money and energy. And fundamental limitations of LLM's. I mean, I'm obviously guessing as well because I'm not an expert, but it's a view shared by some of the biggest experts in the field ¯\_(ツ)_/¯ I just don't really buy the idea that we're going to have near-infinite linear or exponential progress until we reach AGI. Reality rarely works like that.

So far the people who bet against scaling laws have all lost money. That does not mean that their luck won’t change, but we should at least admit the winning streak.
Post reply on HN