Honestly, it never was. Personal projects not withstanding, if there is a product that should always be the focus. Code is only a means to that.

> Even when the model is explicitly instructed to pause due to insufficient tokens

Is there actually a chance it has the introspection to do anything with this request?

Yeah, it does. It was possible with 2.5 Flash.

Here's a similar result with Qwen Qwen3.5-397B-A17B: https://chat.qwen.ai/s/530becb7-e16b-41ee-8621-af83994599ce?...

Ok it prints some stuff at the end but does it actually count the output tokens? That part was already built in somehow? Is it just retrying until it has enough space to add the footer?

No, the model doesn't have purview into this afaik

I'm not even sure what "pausing" means in this context and why it would help when there are insufficient tokens. They should just stop when you reach the limit, default or manually specified, but it's typically a cutoff.

You can see what happens by setting output token limit much lower

No.

"'No Way to Prevent This,' Says Only Nation Where This Regularly Happens"

Now that this guy is selling AI, surprise, surprise, its going to revolution everything else...But its misleadingly written as "we" are cooked.

Its another ad, no?

Look at his submission history, nothing but self promotion. His entire presence here is just an ad.

You both need to take this stuff to hn@ycombinator.com instead of hashing it out here. I think you're wrong, but either way: stop crudding up the threads when all you've got to say is "this person submitted their own post". People do that all the time.

Again: if you think they've crossed the line, the guidelines specifically ask you not take to the threads with it. Mail Dan and Tom. They'll get back to you quickly.

In theory you could use a protocol like this, one where the tools are specified in the page, to build a human readable but structured dashboard of functionality.

I'm not sure if this is really all that much better than, say, a swagger API. The js interface has the double edge of access to your cookies and such.

Have any sickos tried to point AI at SOAP APIs with WSDL definitions, yet?

Likely no.

Every generation needs its own acronyms and specifications. If a new one looks like an old one likely the old one was ahead of its time.

Crypto didn't need vram did it? It was just about hash rate no?

Besides, a 1080 had 8GB, a 5080 has 16GB. Double in 10 years isn't ground breaking. The industry put VRAM into industrial chips. It didn't make it to consumer hardware.

What games have had to deal with instead is inference based up-scaling solutions. IE using AI to sharpen a lower rest image in real time. It seems to be the only trick being worked on at the moment.

I can't think of anything useful crypto did.

One major difference is the code has an owner who might consider what needs a test or ask questions if they don't understand.

To argue that all work is fungible because perfection cannot be achieved is actually a pretty out there take.

Replace your thought experiment with "Is one shot consultant code different from expert code?" Yes. They are different.

Code review is good and needed for human code, right? But if its "vibe coded", suddenly its not important? The differences are clear.

>perfection cannot be achieved

That's not what I get out of the comment you are replying to.

In the case being discussed here, one of code matching the tax code, perfection is likely possible; perfection is defined by the tax code. The SME on this should be writing the tests that demonstrate adhering with the tax code. Once they do that, then it doesn't matter if they, or the AI, or a one shot consultant write it, as far as correctness goes.

If the resulting AI code has subtle bugs in it that pass the test, the SME likely didn't understand the corner cases of this part of the tax code as well as they thought, and quite possibly could have run into the same bugs.

That's what I get out of what you are replying to.

Yeah, seems like this is just ignorance around .vsconfig files. Makes life way easier. You can also just use the VS Build Tools exe to install things instead of the full VS installer, if you plan to use a different IDE.

Can you use .vsconfig to tell Build Tools what your project needs?

Can you generate .vsconfig with Build Tools?

You pass in the --config param to import it.

Exporting this way might be possible but it wouldn't be as useful seeing as it would just grab everything you have installed instead of some minimal set used by some project.

Curl the VS Build tools exe, then run the build tools command to install what's in the .vsconfig.