Hacker Newsnew | past | comments | ask | show | jobs | submit | whatevaa's commentslogin

If CLIs functioned as LLM and you could talk freely with it, there would be no problem. In reality, CLIs are inconsistent and basically function as robotic interfaces, a lot of them not that far of programming.

> If CLIs functioned as LLM and you could talk freely with it, there would be no problem.

On face value, I find this suggestion hilarious. People are having sandboxing issues left, right and center with AI agents and MCPs, so clearly there would be enormous problems with giving an LLM full unscoped terminal access. Remember the guy who had his hard drive wiped?

Do you just mean that the ABIs are inconsistent and you want a more unified way to specify what you want (but the user still more-or-less spells out what command will be invoked)? I have some sympathy for that concern, yes.


If CLIs functioned as LLM and you could talk freely with it, it would kiss your ass while it hallucinates about the files on your hard drives, invent command line switches that either don't do anything or does something other than what you want, and every command that used to take just 5-10 characters would now require you to type paragraphs. No thank you.

Most non-technical users have no idea what they want. They will happily request a feature to implement an email client in your database.

Fine, "what would best serve users", then.

Knowing AMD, shine by doing the same.

My impression for the past decade or so is that Radeon for PC is AMD's way of keeping their GPU division's engine running between contracts for consoles or compute products. At the very least it's a welcome byproduct that provides a competent iGPU and a test bed for future 'main' products. It's been a long while since AMD has shown future vision for PC GPUs or they've led with a feature instead of following what others do.

> My impression for the past decade or so is that Radeon for PC is AMD's way of keeping their GPU division's engine running

During this time AMD was focused on CPUs. They've already said that they'll focus more on GPUs now (since CPUs are way ahead and AI is a thing) so this should change things.


VScode is free, so not really money on the line. Easy decision. Things get complicated when money gets involved.

If you think that just because VSCode is free there's no money on the line, you're not thinking about things the way others do. As I said, reputation alone definitely has a cost and Microsoft has partnerships where VSCode is strategic. They probably just made a calculation that there's not enough users and/or the users using that private API were strategically misaligned with their direction.

Nothing to be surprised about here. First time I'm learning of this existence.

I was also surprised that this would be surprising :)

Not really, these are exceptionaly cases. For most of misdiagnoses or failure to diagnose at all, nothing happens to the doctor.

History shows that either vigilance of most C programmers is not enough, or they are not vigilant at all. C/C++ and RCE via some buffer overflow is like synonyms.

GPU passtrough on a laptop? If GPU is not in a separate IOMMU group I wouldn't even try.

Nowadays these things contain a hidden storage partition to install a driver.

Because you maintain it for her.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: