With a dedicated 3090 (another card for OS) a 34b 5bpw just fits and runs very fast. Like 10-20t/s. The quality is good for my application, but I’m not coding.

CPUs don’t run LLMs.

Even if you get a 3090 with 24gb of vram, you’re going to load the biggest model you can and realize it is useless for most tasks. Less than that and I don’t even know what you would use it for.

If you guys really want to make people care about using crypto for payments, implement Dai Hard on ETH.

https://medium.com/@coinop.logan/daihard-game-theory-21a456ef224e

Basically, it creates a scenario where people can trust each other for anonymous transactions because both parties are highly incentivized to act fairly. This is accomplished by having both parties make a deposit that cab be burned if things go south.

Even if you just make an alias in pfSense and block its traffic, you’re fine.

12.8? That’s nothing.

Very few people on the planet face a threat model where memorizing a seed phrase is worthwhile. Leaving a seed phrase accessible long enough to memorize it considerably increases the likelihood of it being compromised. Locking it up and hiding it immediately greatly reduces this possibility.

You are right about it not being difficult to memorize a seed phrase. It is not hard to do many things that are unnecessary and unlikely to be useful. Only an idiot would fail to realize that such an exercise is essentially pointless, and then proceed to brag about his ability to memorize a few words, while simultaneously demonstrating his inability to reason about basic things.

The only thing Ethereum accomplished is becoming superior money. I wish we could say we had another significant use-case.

For some people “uncensored” means it hasn’t been lobotomized, but for others it means it can write porn.

Nvidia is the only game in town right now. I decided on a 3090 for the time being, with the option of adding another one later. I think in two years we will have 100x better options specifically tailored for AI.

It’s notepad with extra steps.

I think it’s very overkill and you’re going to be sitting at like 10-15% cpu when it’s done. But for projects like this saving a few bucks is not worth it. You need room to grow.

We are very close to the point where people can credibly insist that a real video is a deepfake. But so far I’ve only seen realistic deepfakes where the face is swapped.

When a deepfake of someone actually doing bad things is possible, we will see people claiming the video is fake.

When this is trvial to do, I’m not sure what happens to the concept of security cameras. The recordings may need to be hashed and “notorized” on a blockchain to be legally valid.

I just ordered an ASRock DeskMeet/Ryzen 5 4600G/32gb 3200Mhz DDR4 ($350 all together), for basically the same purpose. But I’m going to use a 512gb NVMe and a PCIE 10gb dual NIC I have on hand. (Hopefully the PCIE NIC actually works in that slot.)

I might try to move Frigate and/or Jellyfin to this device later with hardware accelerated encoding. I like having options.

A good 2.5gb NIC is a 10gb NIC. They negotiate whatever speed they can manage with the hardware and wiring they have. I got a dual port 10gb adapter on Amazon for like $80.

They want to serve more than one or two people, and they want to be able to do so with a simple user/pass scheme.

I have been struggling with crazy judder for months. Now that there is no community, Jellyfin is unusable.

(The forums are pretty much worthless. I got one response from someone who didn’t read my post.)