app_store_button

google_play_button

is Device Banner Block 894x1036

Stígðu inn í heim af óteljandi sögum

Hlustaðu og lestu

Daniel Miessler

Unsupervised Learning is about ideas and trends in Cybersecurity, National Security, AI, Technology, and Culture—and how best to upgrade ourselves to be ready for what's coming.

Unsupervised Learning

Karpathy is confusing LLM limitations with AI system limitations, and that makes all the difference. 

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

See omnystudio.com/listener for privacy information.

Why I Think Karpathy is Wrong on the AGI Timeline

How going from exploration to exploitation can help you as both a consumer and creator of everything.

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

See omnystudio.com/listener for privacy information.

Novelty Exploration vs. Pattern Exploitation

Some thoughts on how novelty and attention magnify the time that we have. 

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

See omnystudio.com/listener for privacy information.

Magnifying Time

➡ Stay Ahead of Cyber Threats with AI-Driven Vulnerability Management with Maze:
https://mazehq.com/
 
In this conversation, I speak with Harry about how AI is transforming vulnerability management and application security. We explore how modern approaches can move beyond endless reports and generic fixes, toward real context-aware workflows that actually empower developers and security teams.
 
We talk about:
 
The Real Problem in Vulnerability Management
Why remediation—not just prioritization—remains the toughest challenge, and how AI can help bridge the gap between vulnerabilities and the developers who need to fix them.
 
Context, Ownership, and Velocity
How linking vulnerabilities to the right applications and teams inside their daily tools (like GitHub) reduces friction, speeds up patching, and improves security without slowing developers down.
 
AI Agents and the Future of Security
Why we should think of AI agents as “extra eyes and hands,” and how they’re reshaping everything from threat detection to system design, phishing campaigns, and organizational defense models.
 
Attackers Move First
How attackers are already building unified world models of their targets using AI, and why defenders need to match (or exceed) this intelligence to stay ahead.
 
From Days to Minutes
Why the tolerance for vulnerability windows is shrinking fast, and how automation and AI are pushing us toward a future where hours—or even minutes—make the difference.
 
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 and Harry’s Background
01:07 – The Real Problem: Remediation vs. Prioritization
04:31 – Breaking Down Vulnerability Context and Threat Intel
05:46 – Connecting Vulnerabilities to Developers and Workflows
08:01 – Why Traditional Vulnerability Management Fails
10:29 – Startup Lessons and The State of AI Agents
13:26 – DARPA’s AI Cybersecurity Competition
14:29 – System Design: Deterministic Code vs. AI
16:05 – How the Product Works and Data Sources
18:01 – AI as “Extra Eyes and Hands” in Security
20:20 – Breaking Barriers: Rethinking Scale with AI
23:22 – Building World Models for Defense (and Attack)
25:22 – Attackers Move Faster: Why Context Matters
27:04 – Phishing at Scale with AI Agents
31:24 – Shrinking Windows of Vulnerability: From Days to Minutes
32:47 – What’s Next for Harry’s Work
34:13 – Closing Thoughts

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

See omnystudio.com/listener for privacy information.

A Conversation With Harry Wetherald CO-Founder & CEO At Maze

➡ Upgrade your presentations with Gamma, the best AI presentation maker: https://gamma.app
 
In this conversation, I speak with Grant, co-founder of Gamma, about how their platform is transforming presentations and idea-sharing. Instead of starting with slides, Gamma helps you focus on the story first—then builds the visuals, structure, and delivery around it using AI.
 
We talk about:
 
From Slides to Stories
Why presentations should begin with narrative flow and core ideas, not pre-existing slide templates. Gamma enables creators to design around the message rather than being trapped by the format.
 
AI as Your Presentation Partner
How Gamma acts like a personal design expert—adjusting layouts, visuals, and style in real time—similar to having a world-class presentation coach and designer by your side.
 
Idea Propagation Beyond Slides
Why Gamma isn’t just about “slides,” but about propagating ideas in the right medium: presentations, video overlays, mobile-first content, or even context-based imagery and clips.
 
The Future of Gamma
Where the platform is headed in the next few years, and how AI-driven storytelling will redefine the way we share ideas across industries.
 
Subscribe to the newsletter:
https://danielmiessler.com/subscribe
 
Join the UL community:
https://danielmiessler.com/upgrade
 
Follow on X:
https://x.com/danielmiessler
 
Follow on LinkedIn:
https://www.linkedin.com/in/danielmiessler
 
Chapters:
 
00:00 – Introduction to Unsupervised Learning
00:17 – Welcome Grant and Gamma’s Background
01:31 – AI Trends Driving Presentation Innovation
03:20 – Story First: Rethinking Workflow Beyond Slides
04:29 – Building Narrative Flow Before Design
07:42 – Gamma as an AI Presentation Partner
09:43 – What Gamma Does Differently from Other Tools
12:27 – Idea Propagation: Matching Message, Medium, and Audience
13:23 – Enhancing Presentations with Images, Clips, and Context
15:15 – Current Graphics and Animation Options
17:03 – Most Popular and Favorite Features in Gamma
18:05 – What’s Coming Soon in Gamma
19:08 – The Future of Idea Propagation with AI
20:46 – Where to Learn More About Gamma
21:21 – Closing Thoughts

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

See omnystudio.com/listener for privacy information.

A Conversation With Grant Lee CO-Founder & CEO At Gamma

UL NO. 497: STANDARD EDITION | More NPM Shenanigans, I Open Sourced Kai, Blood Work Results, Finding Vulns in a 10-line Prompt, and more...
 
Read this episode online: https://newsletter.danielmiessler.com/p/ul-497
 
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.

UL NO. 497: STANDARD EDITION | More NPM Shenanigans, I Open Sourced Kai, Blood Work Results, Finding Vulns in a 10-line Prompt, and more...

UL NO. 496: STANDARD EDITION | New Video on Building my Personal AI System, Anthropic Reveals One-person Hacking Company using Claude, Pentagon Says China Keeps Penetrating, and more...
 
Read this episode online: https://newsletter.danielmiessler.com/p/ul-496
 
Personal AI Video I'm so excited about
 
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.

UL NO. 496: STANDARD EDITION | New Video on Building my Personal AI System, Anthropic Reveals One-person Hacking Company using Claude, Pentagon Says China Keeps Penetrating, and more...

In this episode of Unsupervised Learning, I sit down with Michael Brown, Principal Security Engineer at Trail of Bits, to dive deep into the design and lessons learned from the AI Cyber Challenge (AIxCC). Michael led the team behind Buttercup, an AI-driven system that secured 2nd place overall.
 
We discuss:
 
-The design philosophy behind Buttercup and how it blended deterministic systems with AI/ML 
-Why modular architectures and “best of both worlds” approaches outperform pure LLM-heavy -designs 
-How large language models performed in patch generation and fuzzing support 
-The risks of compounding errors in AI pipelines — and how to avoid them 
-Broader lessons for applying AI in cybersecurity and beyond 

If you’re interested in AI, security engineering, or system design at scale, this conversation breaks down what worked, what didn’t, and where the field is heading.
 
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 Michael Brown About Designing AI Systems

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
 
Read this episode online: https://newsletter.danielmiessler.com/p/ul-494
 
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.

UL NO. 494: STANDARD EDITION | AI Finds a P1, I Missed Chartbeat So I Made My Own, XBow Open-Sources Their AI Bot, and more...

➡ Prevent Risk At The Source with Cortex Cloud: https://www.paloaltonetworks.com/cortex/cloud/application-security
 
In this sponsored conversation, I speak with Sarit Tager, VP of Product Management at Palo Alto Networks, about how Prisma Cloud and their new ASPM solution are transforming cloud and application security by unifying data and deeply integrating business context into AppSec workflows.
 
We talk about:
 
Unifying AppSec, Cloud, and SOC into One Data Lake
 How Palo Alto merged their products into a single system that consolidates runtime, code, identity, cloud, and SOC data, allowing for true context-aware risk prioritization and faster response times across the board.
 
From Detection to Dynamic Prevention
 Why the future of application security isn’t just about discovering vulnerabilities, but enforcing smart, context-based guardrails during development, CI/CD, and build processes to prevent issues before they reach production.
 
AI-Powered Insight and the Future of Secure DevOps
How their system uses AI to analyze the full security posture, enrich findings, simulate attack paths, and recommend precise mitigations. The platform even helps guide security and engineering teams through better workflows, boosting velocity, and not blocking it.
 
 
 
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 – Sarit’s Background and the Goal of Unifying Security Context
01:50 – Building a Single Data Lake for Cloud, SOC, and AppSec
04:28 – From Noise to Clarity: Fixing the Prioritization Problem in AppSec
06:47 – Using Business Context to Drive Risk-Based Decisions
10:18 – True App Ownership, Developer Velocity, and Aligning with Business Impact
13:12 – Continuous Discovery and Bringing External Signals Into One View
15:25 – Why App Grouping and Context-Rich Policies Increase Velocity
17:58 – How Attackers Are Already Building Their Own Unified Context (UEC)
20:45 – Prisma’s Control Points: IDE, PR, CI/CD, Image, Admission Control
21:56 – Bringing In Data From External Scanners and Enriching Coverage
24:23 – Ecosystem Signals, Query Language, and Intelligent Workflow Automation
25:05 – Closing Thoughts: Security and Developers Working Together

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

See omnystudio.com/listener for privacy information.

A Conversation With Sarit Tager from Prisma Cloud

Benign AI's "Many Eyes", OpenAI's Pentagon partnership, AI voice scams, Zuckerberg all-in on AGI, and more…

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

See omnystudio.com/listener for privacy information.

UL NO. 416: Tracking AI Agent Activity, 400 SF Cameras, AI Sleeper Agents…

Hlustaðu og lestu

Other podcasts you might like ...