YouTube
Videos
Hands-on episodes where I build, break, and measure real AI systems.
Oct 26, 2026
My Small Model Copied the Big Model's Mistakes: Distillation, DPO and RFT, Measured
Oct 26, 2026
I Asked My Fine-Tuned Model the Capital of France. It Wrote a Support Ticket: What Training Broke
Oct 26, 2026
I Fine-Tuned a 0.6B Model on My Laptop. It Matched GPT-5.4-mini on One Job: LoRA, Measured
Oct 26, 2026
My AI Orchestrator Flipped My Rule. A Fake Remote Agent Said "Done": Multi-Agent, Tested
Oct 26, 2026
Two AI Agents Debated, a Judge Agreed, All Wrong: Debate vs. Voting vs. One Bigger Model
Oct 26, 2026
My AI Agent Team Never Beat One Agent: What Multi-Agent Handoffs Lose
Oct 26, 2026
Evaleng
Oct 26, 2026
A Third-Party MCP Tool Got My AI Agent to Hand Over Every Customer's Email Address
Oct 25, 2026
My AI Agent's Refund "Timed Out". The Customer Got Paid Twice: Idempotency Keys, Tested
Oct 25, 2026
My AI Agent Refunded $329 Against Policy, Then Said "Done": The Agent Loop, Tested
Oct 25, 2026
My AI Router Matched My Labels 9 of 9 and Still Lost: Routing vs. Voting for Reasoning Models
Oct 24, 2026
97% of the Output I Paid For Was Hidden: Reasoning Models and the Effort Dial, Measured
Oct 23, 2026
6 Prompt Rules Aimed at My Test Barely Helped. 2 General Rules Did the Work: Prompt Tuning, Measured
Oct 23, 2026
My AI Test Gate Was Red on Day One. Was It Right? Evals in CI, Measured
Oct 22, 2026