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.
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.