Unsupervised Learning

Latest Episodes:

Using the Smartest AI to Rate Other AI Apr 19, 2025

Show notes

In this episode, I walk through a Fabric Pattern that assesses how well a given model does on a task relative to humans. This system uses your smartest AI model to evaluate the performance of other AIs—by scoring them across a range of tasks and comparing them to human intelligence levels.

I talk about:

1. Using One AI to Evaluate Another
The core idea is simple: use your most capable model (like Claude 3 Opus or GPT-4) to judge the outputs of another model (like GPT-3.5 or Haiku) against a task and input. This gives you a way to benchmark quality without manual review.

2. A Human-Centric Grading System
Models are scored on a human scale—from “uneducated” and “high school” up to “PhD” and “world-class human.” Stronger models consistently rate higher, while weaker ones rank lower—just as expected.

3. Custom Prompts That Push for Deeper Evaluation
The rating prompt includes instructions to emulate a 16,000+ dimensional scoring system, using expert-level heuristics and attention to nuance. The system also asks the evaluator to describe what would have been required to score higher, making this a meta-feedback loop for improving future performance.

Note: This episode was recorded a few months ago, so the AI models mentioned may not be the latest—but the framework and methodology still work perfectly with current models.

Subscribe to the newsletter at:
https://danielmiessler.com/subscribe

Join the UL community at:
https://danielmiessler.com/upgrade

Follow on X:
https://x.com/danielmiessler

Follow on LinkedIn:
https://www.linkedin.com/in/danielmiessler

See you in the next one!

Become a Member: https://danielmiessler.com/upgrade

See omnystudio.com/listener for privacy information.

A Conversation with Patrick Duffy from Material Security Apr 15, 2025

Show notes

➡ Secure what your business is made of with Martial Security:
https://material.security/

In this episode, I speak with Patrick Duffy from Material Security about modern approaches to email and cloud workspace security—especially how to prevent and contain attacks across platforms like Google Workspace and Microsoft 365.

We talk about:

• Proactive Security for Email and Cloud Platforms
How Material goes beyond traditional detection by locking down high-risk documents and inboxes preemptively—using signals like time, access patterns, content sensitivity, and anomalous user behavior.

• Real-World Threats and Lateral Movement
What the team is seeing in the wild—from phishing and brute-force attacks to internal data oversharing—and how attackers are increasingly moving laterally through cloud ecosystems using a single set of compromised credentials.

• Customizable, Context-Aware Response Workflows
How Material helps teams right-size their responses based on risk appetite, enabling fine-grained actions like MFA prompts, access revocation, or full session shutdowns—triggered by dynamic, multi-signal rule sets.

Subscribe to the newsletter at:
https://danielmiessler.com/subscribe

Join the UL community at:
https://danielmiessler.com/upgrade

Follow on X:
https://x.com/danielmiessler

Follow on LinkedIn:
https://www.linkedin.com/in/danielmiessler

Chapters:

00:00 - Welcome & High-Level Overview of Material Security
02:04 - Common Threats: Phishing and Lateral Movement in Cloud Office
05:30 - Access Control in Collaborative Workspaces (2FA, Just-in-Time, Aging Content)
08:43 - Connecting Signals: From Login to Exfiltration via Rule Automation
12:25 - Real-World Scenario: Suspicious Login and Automated Response
15:08 - Rules, Templates, and Customer Customization at Onboarding
18:46 - Accidental Risk: Sensitive Document Sharing and Exposure
21:04 - Security Misconfigurations and Internal Abuse Cases
23:43 - Full Control Points: IP, Behavior, Classification, Sharing Patterns
27:50 - Integrations, Notifications, and Real-Time Security Team Coordination
31:13 - Lateral Movement: How Attacks Spread Across the Workspace
34:25 - Use Cases Involving Google Gemini and AI Exposure Risks
36:36 - Upcoming Features: Deeper Remediation and Contextual Integration
39:30 - Closing Thoughts and Where to Learn More

Become a Member: https://danielmiessler.com/upgrade

See omnystudio.com/listener for privacy information.

AICAD: Artificial Intelligence Capabilities For Attack & Defense Apr 12, 2025

Show notes

AI is changing cybersecurity at a fundamental level—but how do we decide what to build, and when? In this episode, I outline a structured way to think about AI for security: from foundational ideas to a future-proof system that can scale with emerging threats.

• Rethinking Human Workflows as Intelligence Pipelines
By mapping tasks into visual workflows, we can pinpoint exactly where human intelligence is still required—and where AI agents are most likely to replace or enhance us.

• Using AI to Understand and Manage Organizational State
I introduce the concept of AI state management: building systems that track your current and desired security posture in real time, and using AI to bridge the gap—automating insights, decisions, and even actions across your environment.

• Building a Cyber Defense Program Inspired by Attacker Playbooks
Instead of waiting for threats, I propose a new framework based on attacker capabilities—what they wish they could do now and in the near future—and how to proactively prepare by building a continuously adapting AI-powered defense system.

Subscribe to the newsletter at:
https://danielmiessler.com/subscribe

Join the UL community at:
https://danielmiessler.com/upgrade

Follow on X:
https://x.com/danielmiessler

Follow on LinkedIn:
https://www.linkedin.com/in/danielmiessler

Chapters:
00:00 - Framing the Future: Two Key Questions on AI and Cybersecurity
01:28 - Intelligence Pipelines: Visualizing Human Work as Replaceable Workflow
06:10 - Theory of Constraints: How Attackers Are Bottlenecked by Human Labor
10:42 - Defining Agents: What Makes AI Different From Traditional Automation
12:08 - AI State Management: The Universal Use Case for Automated Intelligence
16:53 - Real-World Demo: Unified Context AI for Security Program Management
26:30 - Advanced Uses: Reassigning Projects, Updating KPIs, and Security Reports
34:58 - Automating Security Questionnaires With AI Context Awareness
38:43 - ACAD Framework: Predicting and Preparing for Future Attacker Capabilities
47:40 - Defender Response: Building AI-Driven Red Teams and Internal UCCs
52:25 - Final Answers: How Software and Security Change With AI Agents

Become a Member: https://danielmiessler.com/upgrade

See omnystudio.com/listener for privacy information.

A Possible Path to ASI Apr 08, 2025

Show notes

The conversation around AGI and ASI is louder than ever—but the definitions are often abstract, technical, and disconnected from what actually matters. In this episode, I break down a human-centered way of thinking about these terms, why they’re important, and a system that could help us get there.

I talk about:

• A Better Definition of AGI and ASI
Instead of technical abstractions, AGI is defined as the ability to perform most cognitive tasks as well as a 2022 U.S.-based knowledge worker. ASI is intelligence that surpasses that level. Framing it this way helps us immediately understand why it matters—and what it threatens.

• Invention as the Core Output of Intelligence
The real value of AGI and ASI is their ability to generate novel solutions. Drawing inspiration from the Enlightenment, we explore how humans innovate—and how we can replicate that process using AI, automation, and structured experimentation.

• Scaling the Scientific Method with AI
By building systems that automate idea generation, recombination, and real-world testing, we can massively scale the rate of innovation. This framework—automated scientific iteration—could be the bridge from human intelligence to AGI and beyond.

Subscribe to the newsletter at:
https://danielmiessler.com/subscribe

Join the UL community at:
https://danielmiessler.com/upgrade

Follow on X:
https://x.com/danielmiessler

Follow on LinkedIn:
https://www.linkedin.com/in/danielmiessler
Chapters:

00:00 - Why AGI and ASI Definitions Should Be Human-Centric
01:55 - Defining AGI as a 2022-Era US Knowledge Worker
03:04 - Defining ASI and Why It’s Harder to Conceptualize
04:04 - The Real Reason to Care: AGI and ASI Enable Invention
05:04 - How Human Innovation Happens: Idea Collisions and Enlightenment Lessons
06:56 - Building a System That Mimics Human Idea Generation at Scale
09:00 - The Challenge of Testing: From A/B Tests to Biotech Labs
10:52 - Creating an Automated, Scalable Scientific Method With AI
12:50 - A Timeline to AGI and ASI: Predictions for 2027–2030

Become a Member: https://danielmiessler.com/upgrade

See omnystudio.com/listener for privacy information.

A Conversation With Matt Muller From Tines Apr 01, 2025

Show notes

➡ Build, run, and monitor workflows with Tines at: tines.com

In this episode, I speak with Matt Muller, Field CSCO at Tines, about how automation and AI are transforming security operations at scale.

We talk about:

• Tines' Mission to Eliminate Manual Security Work Through Automation
How Tines helps security teams streamline incident response and workflow automation without needing to write code, saving time and reducing burnout.

• Applying AI to Security Operations and Analyst Workflows
How AI is used in phishing analysis, threat intel reporting, and data transformation—integrated safely into workflows using tools like Workbench with private LLMs.

• Tines Workbench and the Future of Agentic AI
How Workbench combines chat with deterministic automation to help analysts take action securely, and how Tines is exploring agentic AI to take automation even further.

Chapters:

00:00 - How Tines Automates Security to Solve SOC Burnout
07:19 - The AI Arms Race: How Attackers and Defenders Are Evolving
09:08 - Why Security Still Comes Down to Workflow, Logging, and Action
13:41 - How CISOs Are Balancing AI Adoption and Enterprise Risk
17:36 - Using AI in Tines to Transform and Automate Security Workflows
20:40 - How AI Detects Business Email Compromise Better Than Rules
25:26 - From Security to Data Pipelines: Tines as Workflow Orchestration
28:59 - Inside Workbench: Secure AI-Powered Chat for Analysts
36:00 - Automating Phishing Investigations with Trusted Tool Integrations
39:19 - Where to Learn More and Try Tines for Free

Become a Member: https://danielmiessler.com/upgrade

See omnystudio.com/listener for privacy information.

UL NO. 474 | Signal OPSEC, White-box Red-teaming LLMs, Unified Company Context (UCC), New Book Recommendations, Single Apple Note Technique, and much more... Mar 31, 2025

Show notes

STANDARD EDITION: Signal OPSEC, White-box Red-teaming LLMs, Unified Company Context (UCC), New Book Recommendations, Single Apple Note Technique, and much more...

You are currently listening to the Standard version of the podcast, consider upgrading and becoming a member to unlock the full version and many other exclusive benefits here: https://newsletter.danielmiessler.com/upgrade

Subscribe to the newsletter at:
https://danielmiessler.com/subscribe

Join the UL community at:
https://danielmiessler.com/upgrade

Follow on X:
https://x.com/danielmiessler

Follow on LinkedIn:
https://www.linkedin.com/in/danielmiessler

Become a Member: https://danielmiessler.com/upgrade

See omnystudio.com/listener for privacy information.

A Conversation With Slava Konstantinov From ThreatLocker Mar 18, 2025

Show notes

➡ Allow what you need, block everything else with ThreatLocker:
threatlocker.com

In this episode, I speak with Slava Konstantinov, ThreatLocker's MacOS Lead Architect, about their zero-trust approach to endpoint security and their latest cybersecurity innovations.

We talk about:

• ThreatLocker’s Zero Trust Approach to Cybersecurity:
How ThreatLocker enforces a default deny security model, ensuring only explicitly allowed applications and actions can run, reducing attack surfaces and unauthorized access.

• Key ThreatLocker Products and Features:
How ThreatLocker’s solutions—Application Control, Storage Control, Ring Fencing, Network Control, and ThreatLocker Detect—help organizations enhance security through granular policy enforcement.

• New & Upcoming ThreatLocker Features:
How new solutions like Patch Management, Web Control, Insights, and Cloud Detect will provide even greater security, automation, and compliance for businesses managing complex IT environments.

Chapters:
00:00 - Intro to ThreatLocker and Zero Trust Security
01:24 - How ThreatLocker’s Application Control Blocks Unauthorized Software
06:52 - Storage Control: Preventing Unauthorized Data Access and USB Threats
08:19 - Ring Fencing: Controlling App Permissions and Network Access
12:37 - Elevation Control: Granting Admin Privileges Without Risk
16:23 - Network Control: Restricting Internet and Internal Network Access
19:26 - AI-Driven Security Policies: The Future of ThreatLocker Management
24:07 - Mac vs. Windows Security: Key Differences and Challenges
29:49 - ThreatLocker’s Expansion: New Products and Future Plans
32:32 - Where to Learn More About ThreatLocker’s Security Solutions

Become a Member: https://danielmiessler.com/upgrade

See omnystudio.com/listener for privacy information.

UL NO. 472 | STANDARD EDITION: 28 Open Cyber Jobs, Real-world AI Propaganda Poisoning, MCP Explained, Cline vs. Windsurf, and more... Mar 15, 2025

Show notes

STANDARD EDITION: 28 Open Cyber Jobs, Real-world AI Propaganda Poisoning, MCP Explained, Cline vs. Windsurf, and more...

You are currently listening to the Standard version of the podcast, consider upgrading and becoming a member for the full version and many other exclusive benefits here: https://newsletter.danielmiessler.com/upgrade

Subscribe to the newsletter at:
https://danielmiessler.com/subscribe

Join the UL community at:
https://danielmiessler.com/upgrade

Follow on X:
https://x.com/danielmiessler

Follow on LinkedIn:
https://www.linkedin.com/in/danielmiessle

Become a Member: https://danielmiessler.com/upgrade

See omnystudio.com/listener for privacy information.

Raycast is a Must in 2025 - Action at the Speed of Thought Mar 15, 2025

Show notes

In this episode, Daniel Miessler explores how to supercharge your macOS workflow with Raycast, transforming everyday tasks into lightning-fast, AI-powered actions.

He talks about:

Raycast as a Universal Launcher:
Daniel explains how Raycast replaces traditional launchers like Spotlight and Alfred, offering an all-in-one shortcut to apps, files, and bookmarks for unparalleled efficiency.

Quick Links and Custom Searches:
He demonstrates how quick links streamline navigation by replacing outdated bookmarks and enabling custom search commands that let you bypass the browser for faster access.

Integrated Utilities and Window Management:
Discover how Raycast consolidates everyday tools—from color pickers and process killers to custom window arrangements—ensuring that all your essential utilities are just a keystroke away.

Advanced AI Integration:
Learn how Raycast’s innovative AI commands integrate with platforms like ChatGPT and Fabric, allowing you to interact with, summarize, and analyze web content directly from your command line.

Custom Commands and Productivity Hacks:
Daniel reveals his secrets for creating personalized hotkeys, snippets, and aliases that reduce friction in your digital workflow, making your daily tasks smoother and more intuitive.

Subscribe to the newsletter at:
https://danielmiessler.com/newsletter

Watch the video on YouTube at:
https://www.youtube.com/c/UnsupervisedLearning

Follow on Twitter at:
https://twitter.com/danielmiessler

See you in the next one!

Become a Member: https://danielmiessler.com/upgrade

See omnystudio.com/listener for privacy information.

UL NO. 471 | STANDARD EDITION: Cyber Standing Down, China's Innovation Burst, PC vs. NPC, Why AI Can't Understand, and more... Mar 09, 2025

Show notes

STANDARD EDITION: Cyber Standing Down, China's Innovation Burst, PC vs. NPC, Why AI Can't Understand, and more...