“During the gold rush, sells shovels model” Is a perfect analogy. It worse, OpenAi and similar companies don’t find using any sluice machines profitable. It is basically a gold rush were even the big operations don’t want to be involved with anything, other than selling shovels. This bubble is going to burst and there is an unimaginable about of money invested if this scam.

Undocumented feature flag in a plug-in, that changes the behavior drastically when in any deployment mode.

The funny thing is that reversing the decision proves that they are only interested in money, not customer satisfaction or the product itself.

I think it is too risky to deal with a business that flips on policy, too unpredictable.

We should are least refer to inference LLMs as LLMs. The fact that if you asked it something like who is the current CS2 top team, it would give you the top team at the time it was trained is enough proof that the models effectively know nothing.

Don’t. Unless you are confident you are not adding hot garbage to the code base.

I was in a long term relationship with someone with a drinking problem. When a drunk person says something to you they fucking mean it. Their filter is weaker and, as I label it “they have the courage to say something that they were afraid to say sober.” When you figure this out everything is easier to understand.

The guy at work who managed git before me, well didn’t quite have the knowledge I do and was not using LFS. In one of the main repos a 200mb binary was pushed 80+ times. This is not the only file that this happened to. Even if you do a shallow clone, you still need to add the commit depth eventually. It’s a nightmare.

How does it go when you remove them from a fully pressurized tire? I have only ever removed cores when the tire was empty or had a low amount of pressure.

I am not sure how correct you are but you are probably more correct than a lot of responses.

I don’t remember his music ever being cool or edgy. It was like drinking lacroix when soda is available.

That is kind of funny, sure it parses human speech but when you use the method for communicating letters and numbers very clearly, it breaks.