I learned about Taalas for the first time last week; they're writing AI models directly to chips. Their "chatjimmy" demo is really impressive.
It's a smaller model so it's not as good as the newest models, but the speed is the point.
I learned about Taalas for the first time last week; they're writing AI models directly to chips. Their "chatjimmy" demo is really impressive.
It's a smaller model so it's not as good as the newest models, but the speed is the point.
If you have a fediverse account, you can quote this note from your own instance. Search https://fosstodon.org/users/ehmatthes/statuses/116114366516554587 on your instance and quote it. (Note that quoting is not supported in Mastodon.)