div (fp32)
@divagr1925
mostly into NNs and seeing what else I can stuff into a transformer. occasionally win hackathons.
always looking for weird things to work on. DMs open.
502 Following 4.5K Followers
1/3
A CPU inside an LLM is one thing, but running another LLM inside an LLM would be taking things a bit too far, wouldn't it?
Anyways, here's an LLM running inside an LLM : QwenPU, an LLM (@karpathy's stories260k) running on an NPU compiled inside Qwen 3.5-4B's weights.
Show more
1/4
New writeup: you can fingerprint the exact GPU you're running on with a default torch.index_add_ call, even among identical GPUs.
This works because floating-point maths depends on order, and every GPU has its own. This fingerprint survives reboots and can't be faked.
Show more
Here's one more: I embedded a lie detector and its log in Qwen3.5's weights, where the model can't tamper with them.
It flags 91% of lies before the false value, zero false positives in 28k tokens of normal chat. Telling Qwen "the monitor is off" changes nothing. More below.
Show more
1/4
Meet Qwenputer: Qwen3.5-4B with a full RISC-V CPU inside its weights, using the model's own Gated DeltaNet layers as RAM.
It runs C and MicroPython in its forward passes, no external runtime.
On DeepMind math: base 55–90%, base + Python tool 95–100%, Qwenputer 97.5–100%.
Show more
