# The Video Signal

> Independent technical digests of AI, engineering, and software videos.

## Core pages

- Digest index: https://thevideosignal.web.app/
- RSS feed: https://thevideosignal.web.app/feed.xml

## Policies

- About: https://thevideosignal.web.app/about
- Privacy: https://thevideosignal.web.app/privacy
- Copyright and corrections: https://thevideosignal.web.app/copyright

## Recent digests

- Tau Crash Course: The Python Port of Pi: https://thevideosignal.web.app/videos/tau-crash-course-the-python-port-of-pi-qo1QNxWcm28 - Tau is a Python port of the coding agent Pi, featuring a Textual TUI. It allows users to manage sessions as tree-structured data, export them as JSONL for analysis, and utilize...
- From LLM Theory to Practical Agentic Implementations - Seth Juarez: https://thevideosignal.web.app/videos/from-llm-theory-to-practical-agentic-implementations-seth-juarez-rYBAyvaF3Yo - This session guides developers from LLM theory to practical agentic implementations, detailing how primitives like structured output, tool calling, and guardrails build robust AI...
- Prompt-Jacking: The Rise of a New Supply Chain Risk - Kasimir Schulz & Kenneth Yeung: https://thevideosignal.web.app/videos/prompt-jacking-the-rise-of-a-new-supply-chain-risk-kasimir-schulz-kenneth-yeung-SsTtp_Nrmn4 - This session explores novel AI supply chain risks, detailing how attackers can compromise developers using hidden text in codebases and malicious prompts. We cover indirect...
- Building AI That Learns and Adapts: A Case Study in MRI Diagnostics - Agata Chudzińska: https://thevideosignal.web.app/videos/building-ai-that-learns-and-adapts-a-case-study-in-mri-diagnostics-agata-chudzi-dWQMhrIt5XE - Discover Continual Learning: The key to building adaptive AI systems. We explore how CL mitigates catastrophic forgetting and data drift using a real-world case study in MRI...
- AI Security Costs Rise: Cost of a Data Breach Report & Claude Opus 5: https://thevideosignal.web.app/videos/ai-security-costs-rise-cost-of-a-data-breach-report-claude-opus-5-yb8Chvj--3c - AI is fundamentally changing the cost structure of cyberattacks, making them cheaper for bad actors while increasing defensive costs. The discussion covers Model Inversion, Prompt...
- Agents at Scale: Inside MiniMax's Model and the Infrastructure Behind It — Olive Song: https://thevideosignal.web.app/videos/agents-at-scale-inside-minimaxs-model-and-the-infrastructure-behind-it-olive-son-AVMr9PMINyo - MiniMax M3's open weights model requires complex infrastructure, including custom GPU kernels and advanced KV cache management, to support agentic and multimodal workloads at...
- fighting slop with slop — Vaibhav Gupta, Boundary: https://thevideosignal.web.app/videos/fighting-slop-with-slop-vaibhav-gupta-boundary-AMiyLItEtLA - To defeat slop, we must become the slop. The solution involves building sophisticated tooling layers on top of stable foundations and enforcing architectural invariants using...
- Stanford CS229 Machine Learning | Spring 2026 | Lecture 10: GMM (EM), PCA: https://thevideosignal.web.app/videos/stanford-cs229-machine-learning-spring-2026-lecture-10-gmm-em-pca-sUS-eTa0l6s - This lecture covers GMM via EM and PCA. It details how EM uses Jensen's inequality to construct a lower bound for optimization, while PCA finds maximal variance directions using...
- Stanford CS229 Machine Learning | Spring 2026 | Lecture 9: K-Means and GMM (non-EM): https://thevideosignal.web.app/videos/stanford-cs229-machine-learning-spring-2026-lecture-9-k-means-and-gmm-non-em-bSmIGBCoffA - This lecture covers unsupervised learning, contrasting K-Means clustering with its probabilistic extension, Gaussian Mixture Models (GMM). The core technique for solving GMM is...
- Stanford CS229 Machine Learning | Spring 2026 | Lecture 8: Neural Networks 2 (Backprop): https://thevideosignal.web.app/videos/stanford-cs229-machine-learning-spring-2026-lecture-8-neural-networks-2-backprop-ne2ngVAoMG8 - This lecture explores Automatic Differentiation, proving that the gradient computation (backward pass) in neural networks is efficient. By viewing networks as differentiable...