Riots

Goal state lol:

https://www.afternow.io/content/images/2016/10/virtual_reali...

is this bad for my SSD?

What do you mean 'resets on the bench?

When OpenAI do quota resets (not your scheduled weekly ones, the promotional or apology resets) they don't just reset whatever quota you were on. They give you a token to reset your weekly quota when you like.

They added this a few weeks ago.

Before, they would do their celebrated usage resets while I was behind the already generous weekly quota.

If I had 80% left on Friday to spend over the weekend, they would reset and I'd have 100% until next Friday, a potential net negative.

OpenAI listened to the complaints.

all useful models are proprietary.

the most useful frontier models maybe. but you cant say deepseek or glm is useless. thats not even a debate.

Those are still both proprietary. Open weights != open-source

Sorry, please elaborate.

Imagine being asked to publish 'beautiful' code for an audience comfortable with doing so themselves. On top of all the theory and practice needed to produce a complete system you're expected to develop a point of view your peers want to engage with.

>contemporary rich country education systems

I'm from such a country and this tracks. I often look to individuals of the past with the same academic credentials as me and it seems they are much better read & educated. And when I was in school, it often felt like my education was diluted to cater to the LCD.

Less worldly, how so? Been considering an FT sub.

When I studied economics and finance, I thought it was very dumb that we created a position where an individual's words can have that kind of power.

Yeah, but despite that they work pretty good lately if what you're asking is verifiable, like searching for the name of a book.

If you think of it as lossy compression algorithm that makes sense.

"There is a book about a boy in a magical school, with friends, who fights a big bad and its called ..."

should have Harry Potter as the highest possible response. But that is not the answer based on a truth model, just a statistical average. You could have been looking for Earthsea series. Or it could have the heat turned up and decide to go for a hallucinated answer over the statistically most likely token.

If you want a verifiable answer your best options would be to have the heat turned to 0, but that means it cannot create new responses. Or if you have heat, to ask 4 times and sample the avg. But at that point what is the advantage over just googling it?

And one shooting your answer and hoping its the bell curve answer is going to have decent results but its also proveably going to fail in a non insignificant number of cases

> If you want a verifiable answer your best options would be to have the heat turned to 0, [...]

I don't see how that helps? If you just want the same answer multiple times in a row, you could just write down the seed of your pseudorandom number generator?

> And one shooting your answer and hoping its the bell curve answer is going to have decent results but its also proveably going to fail in a non insignificant number of cases

Setting the temperature to 0 doesn't guarantee you get a good answer either.