I would not say Johnny Harris is a reliable source

Anyone from the local llama communities experienced with Gemma models?

I’ve heard good things but I only use Mistral because it’s proved the most versatile.

I’ve been curious about google coral, but their memory is so tiny I’m not sure what kinds of models you can run on them

If nothing else the atproto is pretty great, we’re starting to see a proper federated net start opening up around it.

Waiting for a 8x1B MoE

Anyone else remember when people were making expert systems with scheme and saying that was the end of doctors etc?

Ironically thanks in no small part to Facebook releasing Llama and kind of salting the earth for similar companies trying to create proprietary equivalents.

Nowadays you either have gigantic LLMs with hundreds of billions of parameters like Claude and ChatGPT or you have open Models that are sub-200B.

I could be mistaken too, this has all only recently become interoperable so there’s some growing pains

Isn’t that what Whitewind is doing?

Yes! Actually.

The full atproto up and running with bluesky is only in the last month or so, so people are finally starting to trickle out and set up their own services and hosts.

It’s actually very promising and hopeful.

This doesn’t seem to be that big an issue as PDS’s can just directly communicate with one-another like how ActivityPub works.

I wouldn’t lump bluesky in the same pile as threads anymore, the atprotocol is fully up and running and slowly but surely individually hosted data servers are trickling out and away to their own services.

There’s even new services running completely independent of bluesky running on atproto now: https://whtwnd.com/about

There’s a really good write-up on how atproto federation works here: https://whtwnd.com/alexia.bsky.cyrneko.eu/3l727v7zlis2i

If you treat an AI like anything other than the rubber duck in Rubber Duck Programming you’re using it wrong.

Like that person in a dream who keeps telling you to wake up

Alongside the EPA for constantly getting in the way of the FAA trying to slip his SpaceX flight licenses through with a wink and a nudge instead of properly following regulations, and the FAA for trying to keep a semblance of legality through the whole process.

Less like surrogates and more like The Muppets

SpaceX launched about 429,125 kg of spacecraft upmass in Q1, followed by CASC with about 29,426 kg

Smaller satellites (<1,200 kg) represented 96% of spacecraft launched in Q1, 76% of total upmass

So the way I’m personally reading this is 2/3 of this is starlink launches

Easiest? Tailscale., set it up on the server and each client you want to access it and it creates auto-resolving P2P VPN tunnels between them all.

I still think it’s better to refer to LLMs as “stochastic lexical indexes” than AI

SLS is on track to be more expensive when adjusted for inflation per moon mission than the Apollo program.

You do realize that Artemis III requires 15 Starship launches just to fuel the thing enough to get to the moon? Why are you comparing it to Apollo?