

Don’t stop it. It’s healthy.
Doing the Lord’s work in the Devil’s basement
Don’t stop it. It’s healthy.
Notch? The guy who codes in java?
Its frameworks still have issues with basic stuff like many to many relationships.
Not sure what you mean by that. Do you mean ORMs? Which one and when did you try it?
Same, I’ve been looking for something like that for quite some time
If I had to guess, I’d say it’s not necessarily baked into the models, but rather part of a style guide in the system prompt
Good luck finding enough wood for that ! Energy was reaaaally expensive back then.
They had sewage and toilets since Roman times. It wasn’t affordable to many (and you couldn’t make it affordable) but they definitely knew how to make it.
I’d just like to interject that while traveling was rare in medieval times, it did happen. People usually didn’t get thrown in jail for it, even if they didn’t speak the local language.
Regular people didn’t really speak Latin beyond a few bits of prayer. The lingua franca was a mix of various coastal languages (think of the belter patois in the expanse), but even that was only known to traders.
You’d have a tough time for sure, but wouldn’t necessarily get in trouble.
They do math, just in a very weird (and obviously not super reliable) way. There is a recent paper by anthropic that explains it, I can track it down if you’d be interested.
Broadly speaking, the weights in a model will form sorts of “circuits” which can perform certain tasks. On something hard like factoring numbers the performance is probably abysmal but I’d guess the model is still trying to approximate the task somehow.
I am looking for a solution for a ~1TB collection, and the Glacier Deep Archive storage tier is barely above 1$/m for the lot. You may want to look into it ! If I remember correctly, the retrieval (if you one day need to get your data back) was around 20$ to get the data in a few hours, or 2$ to get it in a couple days.
Java is actually twice faster cause the name is twice shorter