3:22Transcript
Why Smaller Language Models Hallucinate More. I Turned Down $475,000.
Why smaller language models hallucinate more. Senior AI engineer. I turned down $475,000. More weights and more data make a more accurate function.
NEXUSTRADE / VIDEOS
AI trading videos
Shorts I filmed while building NexusTrade.
Every video has a transcript.
184 shorts · every one transcribed
Machine learning videos
Start watching ↗3:22Transcript
2:26Transcript
Can AI Improve Qwen by Editing Its Weights?
Direct Qwen3.5-9B weight editing with Codex: the saved checkpoints, random controls, a repetition-loop fix and the actual nine-case grading results.
2:51Transcript
LLM Judge Training Data: My AI Checker Changed 12 of 29 Grades
How I built the answer key for my AI critic: real agent runs, an AI checker that changed 12 of 29 grades, and blind review that left 889 trusted examples.
0:13Transcript
A Neural Network Is a Universal Function Approximator
A short screen recording contrasts a model-selection question with an AI-assisted development conversation. The original on-screen content is preserved, wi
0:46Transcript
Can NSGA-II find a better spot for your router?
Watch gradient descent and NSGA-II optimize router placement in a simulated home, with a flat coverage loss, equal evaluation budgets, and different starts.