Ah yes, of course.
I was just explaining that while its context is indeed reset basically reset at every conversation, because the models can’t really learn by doing like we do, the conversation do end up in later model updates.
So both these things are true.
It’s called “post training”. It’s of course not learning anything during your interactions, but every now and then they take a bunch of this data and use it to improve the model a little more, and that’s when you go from opus 5.3 to opus 5.4.
Careful with this hashes in the first position of a row…
And that’s going to he the new default platform for smart ovens or something?
Because Anthropic up there Is claiming that LLMs can propagate through IoT devices.
That stuff couldn’t run on my good laptop if I wanted to…
There is no stock. It’s a private company still.
a burning code dumpster of epic proportions
a burning code dumpster of Epic proportions
FTFY
Oh, he already has AutoCad, called cadcraft.
Feel free to try it out and let me know how well it works.
It’s written basically as if the reader is also expected to be American.
Which annoyed me.
But I’ve had a rough week. Never mind me.
Americans are the only ones who fly to American cities without getting scanned… Because it’s an internal flight.
I don’t think there’s a corner left in the industrialized world where you can go through passport control at the airport without getting your face scanned. At least as a foreigner.
Tell me you’re from the US without telling me you’re from the US.
I think you have your Greek references a bit mixed up.
It was allegedly used by Leonidas at the Thermopylae. Towards the Persians.