Video library

One technical idea per video. Full evidence one click away.

Explore 46 native-English explanations published on 5sigmas. Every watch page connects the short explanation to its original chapter and related material.

46 videos available

0:48

AI security · 0:48

Production Controls

Which controls limit damage when an AI system reads external content, uses tools and one defense fails.

Separate document reading from actions · Give every tool only the permissions it needs
0:48

AI security · 0:48

Red Teaming

How to test from the document that enters the system to the action it can execute, before an incident occurs.

The threat model comes before the benchmark · Separate what the model can do from what the system executes
0:48

AI security · 0:48

Poisoning

What happens when a document or memory preserves a dangerous instruction and the system uses it again later.

Storing a datum does not make it true · Persistent memory is already a measurable attack surface
0:48

AI security · 0:48

Jailbreaks

How an attacker tries many ways of asking for the same thing and which controls remain necessary after a refusal.

Refusing a request does not create a perfect boundary · Trying many variants changes the cost of the attack
0:48

AI security · 0:48

AI Security

A series on how an instruction hidden in a document can influence an AI system, how that risk can persist and which controls constrain actions.

Contents · 1. An instruction hidden in a document can change what the system does
0:32

AI agents · 0:32

From demo to production

What it takes to run an AI agent in production: budgets, retries, idempotency, observability, asynchronous work, fallbacks, and criteria for not using an agent.

Budgets before promises · Retries, idempotency, and terminal failures
0:32

AI agents · 0:32

Agent security

Why an agent that reads external data can be manipulated into acting, and which controls reduce risk: instruction separation, least privilege, approval, and auditability.

Direct and indirect prompt injection · Authorization must live outside the prompt
0:32

AI agents · 0:32

How to evaluate an AI agent

Evaluating an agent requires measuring the whole task, traces, tools, cost, and recovery from failure. A convincing final answer is not enough.

The unit of evaluation is a task · Four dimensions worth measuring
0:32

AI agents · 0:32

AI Agents

Five chapters to understand what an AI agent is, how it uses tools, how to evaluate it, which risks it introduces, and what it takes to operate one in production.

Contents · 1. What an agent is—and is not
0:53

Infrastructure · 0:53

The real footprint of a data center

Water, energy, minerals and data-center lifecycle: what AI consumes, why impact varies by location, and how to measure its footprint.

1. The comparison that calibrates the conversation · 2. Water: withdrawal, consumption and the technology that determines it
0:53

Infrastructure · 0:53

Energy, heat and connectivity

Why the cold of space does not mean free cooling, where the real advantage of orbital energy lies, and what limits the connection to Earth imposes.

1. Why the cold of space does not mean free cooling · The real scale of radiators
0:53

Infrastructure · 0:53

Why now

Why orbital computing is being discussed now. The pressure AI compute demand places on terrestrial infrastructure and the limits that make space relevant.

1. The explosion in compute demand · 2. Terrestrial bottlenecks
0:48

AI security · 0:48

Prompt Injection

How an instruction hidden in a document can enter an AI system and which controls separate reading from action.

1. The problem starts when a document reaches the model · 2. The instruction can appear in a document search
0:20

Systems engineering · 0:20

Proactive and reactive agents and tool calls

A technical walkthrough of Reactive / Proactive Agent and the conversational contract it encapsulates: immediate response, asynchronous work, and deferred completion.

The problem is not the tool, but time · The first turn accepts work; it does not promise results
1:00

Reasoning · 1:00

Test-Time Compute

Test-time compute as a second scaling axis. The three levers—more steps, more candidates and more structure—and their quality, cost and latency tradeoffs in reasoning models.

1. What test-time compute is and why it matters · 2. The three levers
1:02

Economics, energy and well-being · 1:02

AI and GDP Today

Why AI's macroeconomic impact takes time to appear in GDP, where it appears earlier, and which signals are most indicative of what is happening.

1. Why macro impact takes time to arrive · The four mechanisms behind the lag
0:59

Reasoning · 0:59

How Reasoning Fails

Sycophancy, shortcut learning, specification gaming and cascading failures: the failure modes of reasoning models, how to detect them and how to mitigate them.

1. Failure types · 1.1 Shortcuts — shortcut learning
1:02

Economics, energy and well-being · 1:02

Measurement: GDP vs Well-being

Why GDP does not capture real well-being, which dimensions matter most, and when subjective well-being diverges from material well-being.

1. What GDP measures and what it leaves out · What GDP leaves out
0:58

Reasoning · 0:58

What It Means for an LLM to Reason

What reasoning means for a language model, what o1 and DeepSeek R1 added, and why evaluating reasoning requires looking at steps, cost and failure modes.

1. What "reasoning" means for a human · 2. What LLMs can do that looks like reasoning
0:45

Reasoning · 0:45

Reasoning Models

Five chapters on how LLMs reason: test-time compute, failure modes, latency, cost and risks when models use tools.

Contents · 1. What "reasoning" means for an LLM
1:02

Economics, energy and well-being · 1:02

Electricity and Well-being

Why reliable, affordable electricity enables real gains in health, logistics and industry, and the difference between having kilowatts and having supply quality.

1. The four main channels · Health
1:02

Economics, energy and well-being · 1:02

AI, GDP, Well-being and Energy

Quantitative analysis of AI's impact on energy, productivity and well-being using real World Bank, IEA and Penn World Table data rather than speculative projections.

Contents · 1. Electricity → well-being: the real mechanisms
1:02

Multimodality · 1:02

Evaluating Multimodal Systems

How to evaluate multimodal systems without confusing benchmarks with real capability: OCR, audio, grounding, reasoning and metric failures.

1. What it means to evaluate grounding · 2. The problem of benchmark contamination
1:02

Multimodality · 1:02

Multimodal System Architectures

Four multimodal architecture families, their differences in quality, cost and latency, and when each way of combining modalities makes sense.

1. Visual encoder + connector + language model · 2. Fusion through cross-attention
1:02

Multimodality · 1:02

Alignment: From Pairs to Interactions

How models learn that different signals describe the same content, and why data quality determines the robustness of multimodal alignment.

1. Image–text pairs: the foundation and its limits · 2. Beyond the pair: aligning multiple modalities
1:02

Multimodality · 1:02

The Real Problem of Multimodality

What it means to integrate text, images, audio and other modalities, and how perception, alignment, reasoning, generation and action fit together.

1. A modality is not only an input type · 2. The problem is not adding modalities, but crossing them without destroying them
1:02

Multimodality · 1:02

Multimodality in Generative AI

What it means to build systems that can perceive, align, reason, generate and act across text, image, audio, video, documents and other signals from the world.

Contents · 1. The real problem: what counts as multimodality
1:03

History of AI · 1:03

Beyond the Transformer

How the field is trying to move beyond pure Transformer scaling by combining tools, search, inference-time memory, world models and robotics.

1. Why the Transformer is no longer a complete map · 1.1 Truth, uncertainty and hallucination
1:03

History of AI · 1:03

Learn — from rules to data

How AI moved from hand-written rules to learning from data: expert systems, statistics, neural networks and the AlexNet breakthrough.

1. The age of rules: when intelligence was written by hand · The first symbolic systems
1:03

History of AI · 1:03

Mechanize — from calculation to computing

How humanity automated calculation: from the first physical mechanisms to the separation of program and hardware, and the theoretical foundations of modern computing.

1. From automating calculations to programming procedures · The first calculators: automation is not programming
1:03

History of AI · 1:03

From the Caves to AGI

An intellectual history of AI: from the first mathematical abstractions to foundation models. Mathematics, philosophy and computing in context.

Contents · 1. Represent (≈ 40,000 BCE – 1700)
1:03

Foundations · 1:03

What is Generative AI?

How generative AI works: from embeddings and the Transformer to foundation models. Scaling laws, LLMOps, and differences between LLMs, RAG, and agents.

1. Embeddings: Translating text into numbers · 2. The Transformer: The architecture that changes everything
1:03

Foundations · 1:03

What is AI?

What Artificial Intelligence is, how it works and how it evolved: from heuristics and Machine Learning to neural networks and foundation models.

1. The General Framework: AI, ML, DL and GenAI · 2. How do these systems learn?