Plan 9

Need max AVX instructions. Anything with P/E cores is junk. Only enterprise P cores have the max AVX instructions. When P/E are mixed the advanced AVX is disabled in microcode because the CPU scheduler is unable to determine if a process thread contains an AVX instruction and there is no asymmetrical scheduler that handles this. Prior to early 12k series Intel, the microcode for P enterprise could allegedly run if swapped manually. This was “fused off” to prevent it, probably because Linux could easily be adapted to asymmetrical scheduling but Windows would probably not. The whole reason W11 had to be made was because of the E-cores and the way the scheduler and spin up of idol cores works, at least according to someone on Linux Plumbers for the CPU scheduler ~2020. There are already asymmetric schedulers in Android ARM.

Anyways I think it was on Gamer’s Nexus in the last week or two that Intel was doing some all P core consumer stuff. I’d look at that. According to chips and cheese, the primary CPU bottleneck for tensors is the bus width and clock management of the L2 to L1 cache.

I do alright with my laptop, but haven’t tried R1 stuff yet. The 70B llama2 stuff that I ran was untenable for CPU only with a 12700 with just CPU. It is a little slower than my reading pace when split with a 16 GB GPU, and that was running a 4 bit quantization version.

deleted by creator

deleted by creator

deleted by creator

deleted by creator

deleted by creator

It is just a fundamental abstraction that it is an all Israeli thing. Israel has no separation of business government and military. It is one of the most integrated States in that respect. The person with the most influence and control over the alignment problem and the most proprietary undocumented black box aspect of all present AI, so close to the Israeli military is not a good idea. Israelis have proven that they are genocidal nuts with no ethics. Even with the best intentions, will these people maintain them under torture and duress. We are all only animals that cosplay sentient intelligence. The power available by bending alignment is already so large it can reshape all of civilization if it were removed or realigned and that power is only going to increase with time.

deleted by creator

Not unless an http port is open too. If the only port is https, you have to have the certificate. Like with my AI stuff it acts like the host is down if I try to connect with http. You have to have the certificate to decrypt anything at all from the host.

Sorta, you have to install your certificate authority into the browser and it might complain about verifying that but it will still connect with the encryption.

deleted by creator

I mean more like a self signed TLS certificate with your own host manually set in the browser. Then only make the TLS port available, or something like that. If you have access to both(all) devices, you should be able to fully encrypt by bruit force and without registering the certificate with anyone. That is what I do with AI at home.

Anyone else notice they have a sexual preference in singers and music? I mostly like metal, and there are a few female singers I have liked, though I’m out of touch, having been totally disenfranchised by streaming, and bad with names in general. I tend to wear thin on female vocals. I don’t know if it is the tone, texture, or content.

I used to put 5 CDs in a turn table boom box in my auto body shop and just let them play while I worked for 12-16 hours straight. It was mostly like Disturbed, Slipknot, Metallica, Alice in Chains, that kind of stuff. I can’t recall any of the female stuff I tried, but I never kept them in the loop for very long. Dunno why really. Guess I’m music-gay like Red team

I’ve half ass thought about this but never have tried to actually self host. If you have access to all devices, why not just use your own self signed certificates to encrypt everything and require the certificate for all connections? Then there is never a way to log in or connect right? The only reason for any authentication is to make it possible to use any connection to dial into your server. So is that a bug or a feature. Maybe I’m missing something fundamental in this abstract concept that someone will tell me?

If humans are your pets, you are a slave owner

I don’t get why anyone views being a moderator like ownership. It seems to attract a lot of narcissism in that mindset. I don’t think mod posts are relevant to growing a community. Quite the opposite, I think forced posts are worse than none. It is a matter of how the community resonates with users and the total number of people on the platform. The more niche the group, the harder it is to find an audience. The community belongs to users that post. The only community truly owned by a mod is the one where they are the only one that posts. Mods serve the community not the other way around.

Pray to Luigi

In nearly every instance you will be citing stupidity in implementation. The limitations of generative AI in the present are related to access and scope along with the peripherals required to use them effectively. We are in a phase like the early microprocessor. By itself, a Z80 or 6502 was never a replacement for a PDP-11. It took many such processors and peripheral circuit blocks to make truly useful systems back in that era. The thing is, these microprocessors were Turing complete. It is possible to build them into anything if enough peripheral hardware is added and there is no limit on how many microprocessors are used.

Generative AI is fundamentally useful in a similar very narrow scope. The argument should be limited to the size and complexity required to access the needed utility and agentic systems along with the expertise and the exposure of internal IP to the most invasive and capable of potential competitors. If you are not running your own hardware infrastructure, assume everything shared is being archived with every unimaginable inference applied and tuned over time on the body of shared information. How well can anyone trust the biggest VC vampires in control of cloud AI.

Mixture of Experts