There was an interesting bit of research that qwen has a single neuron that makes it “demonic evil qwen” and a simple “Who are you?” will get some absolutely terrifyingly vile results.
Anyways, what I’m trying to say is I want evil qwen to be my CPU.
Have you any idea how it feels to be a Qwenputer living in a Qwenbot's Qwenputer's world?
> When Qwen 'saves' a file, the compiled layers hash its name into one of 1,024 slots in a directory kept in the DeltaNet state, and store the text itself in other heads, with eight tokens per row, chained together
I’ve never wanted to learn how LLMs work more than reading this. Fascinating.
Does divagr get paid to do wild things with LLMs? Just curious if they’re being compensated for these wild experiments
It could be interesting to experiment with more complex representations in the memory/file system, i.e. vectors. Seems like the full advantage of this architecture is yet to be explored. Blending neurons with deterministic compute to fit on one GPU is a fascination concept, never considered it before!
I'd be very interested in how a scratch trained model that started training with this neural circuitry would behave. Especially the storage space.
But can it run Doom?
How much VRAM do I need to run DOOM?
Makes me want to run agents on it
No, I don’t want you to use the computer, I want you to be the whole computer. No mistakes.
This is cool and I understand the RAM emulation with gated attention but how does the CPU emulation wor? You add layers that are then trained to predict outputs while interpreting RISC instructions?
Cool cool cool
[flagged]
If anyone else has an easier way to emulate RISC-V I’d like to hear it. /S
But... why? </s>
This reminds me of C++ Template Metaprogramming (TMP) (it's Turing-complete so people wrote "games" that run at compile time). The same with TypeScript types, I think someone got DOOM running entirely in the TypeScript type system. An interesting tech demo but entirely superfluous.
So this is yet another rube goldberg machine.
We have gone down this path already in [0] and this is the same thing but overly complicated. This reason is "because LLMs".
Why?
This is fun and games, but wait until an agents finds this and does the most misaligned thing with it in order to fold paper clips.
> Because a CPU inside a language model clearly wasn't cursed enough, I decided the prudent thing would be to give it a filesystem too.
Love the spirit :)