xydac

just wait till someone builds a idea generator model - wire it to decision (jev-like) classifier -> loop it back to researcher

>> may be thats what open ai did :)

i wonder what it means for maths researchers, and how it aligns with how they approach math problems.

did you find a specific one on aliexpress. am thinking the same on why this even requires a waitlist

yes, share performance, numbers if you can, also i wonder if you figured out a way to do a 2way audio with local models, or even explored that. I have a very similar setup but not too happy with the token speed, will try omlx though !!!

Yes, it did, Pair that with first snow of my life :D

Oh ! i cannot see myself doing php again, loved the language and have some good memories too but that me was 10 years ago

I was probably thinking of a future where future devices from education institutions would have these preloaded with a non modifiable version of agents guardrails tuned for learning...

This is a very good baseline for future courses to build on, there would always be a group that wants to jailbreak this and thats okay, but have baseline agent support learning is needed in this ai first world.

some of these would have made to embedded hardwares, making updates more challenging if say you were to flash an update.

this is interesting, we should wire this to frontend design system library that automatically helps user use these palette.

Its crazy how many similar threads exists today.

classic, crowdsource it to other cities !!

its funny how us developers build varied UX, but nothing beats the simplicity of HN's default experience. quick and bloat free.

Mine bailed out on a Baseband error due to which i am not even able to boot it anymore :(

looks nice, wonder what would take to hook this to a database connection directly

This is cool, haven't run this yet but seems really promising. Am thinking how this can be a super useful to hook with internal corporate search engines and then get answers from that.

Good to see more of these non API key products being built (connected to local llms)

this is first time i have read something completely in a long span of time !!

exactly, and pair that with css variables for customizations if needed for ad-hoc projects/prototypes or full products

have been following the development of this very closely for this library, and love the fact that we can script load individual web component in html as bare bones.

cool concept, love the idea. Might be fun to integrate with local llama to get most privacy

This is an amazing idea as well as execution providing best use of resources to end users.

Soon Samsung would be like able to show moon and Saturn twogether in their photos

This is amazing, kudos to the team

This is why i love HN comments, Good luck for your product !

So wondering if one of the hilly roads on San Francisco might be on top of a buried ship..!!!

It was a rant !! Am sure am not the only one who uses Chrome and get pissed when it shows that screen..

I use NextCloud for personal cloud backup solution. Although it doesn't have mail server in it.

I would use Nextcloud, Its pretty neat and you can also use WebDAV

Edit : Just in case you were looking for something Selfhosted.

That's interesting to know. A Body css without a <body> tag..!!

Best one is

/ * This should never happen exception. Use in situation that really shouldn't happen...NEVER * * */ public class NeverHappenException extends RuntimeException {