hoschicz

they showed a banana in the payload bay, that was the testing payload:)

they pushed the rocket to the limits in this flight

How is context-from-following-tokens implemented in the pure OAI API? I assumed there must be specialized models that have two separate context windows.

I use one with 16 GB and it's fine, 0 issues whatsoever.

2 years right

I'm seeing that they just updated it today on the URL you linked

So this means now they're no longer free I suppose :(

Can you give some examples of the low-power x86 boxes? As of my last knowledge update :) none of them took off

They _really_ should give a dump of all the torrents, magnet links and seed/leech counts...

You can easily decentralize search, but not fetching seed/leech counts essentially

- they are working on a stateful API - they are working on a cheaper version of GPT-4

Most probably this is driven by their use of it in ChatGPT, which is on fire from PMF. Clearly they're experimenting with the cheaper GPT-4 in ChatGPT right now as it's fairly turbo now, as discussed earlier today.

Absolutely. I am guessing they quantized the model (run it not in 32-bit but say 8-bit, saves resources). Just like they did with 3.5-turbo.

It's behind a waitlist

this is GPT 3.5, the icon is green