This site uses a cookie to remember your theme preference. No tracking or third-party cookies are used. See our Privacy Policy for details.

#RealTalk with Aaron Bregg Podcast Logo
  • Home
  • About
  • Learning
  • Search
  • Contact
  • Privacy

Categories

  • AI Agents (9)
  • AI Industry Watch (29)
  • AI Security (45)
  • MCP Security (3)
  • Non-Security (5)
  • Security Tools (1)
  • Threat Intelligence (1)

Tags

Agentic AI (4) AI Ethics (2) AI Governance (8) AI Models (3) AI Regulation (4) AI Research (2) AI Security (8) Authentication (2) Authorization (2) Bug Bounty (1) Enterprise AI (6) Future of Work (4) Healthcare AI (8) OWASP (1) Phishing (1) Secure Code (2) Social Engineering (2) Vendor Risk Management (1)

Recent Posts

  • The Four Types of AI Agent Memory — and Why Each One Is a Healthcare Security Concern Jun 17
  • The Expert Generalist and the Hourglass: How Agentic AI Is Reshaping Team Structures — and What Healthcare Security Leaders Should Do About It Jun 16
  • Fable 5 / Mythos 5 Suspension: The Background Story — Amazon, a 90-Minute Ultimatum, and What It Means Going Forward Jun 15
  • Kali365 PhaaS Kit Hijacks Microsoft 365 OAuth Tokens and Bypasses MFA — What Healthcare Security Teams Need to Do Now Jun 14
  • Anthropic's Fable 5 and Mythos 5 Access Suspended by Government Export Control Directive Jun 13

Theme

© 2026 Bregg Holdings LLC

#RealTalk with Aaron Bregg

Latest Healthcare Security Insights

Experienced analysis, tutorials, and best practices in cybersecurity

AI Security

Small Models, Big Impact: Why Healthcare Doesn't Need Mythos to Find Vulnerabilities

One day after Anthropic announced Claude Mythos was too dangerous to release, security startup AISLE showed that $0.11/M...

Apr 21, 2026 16 min read
Read More
AI Security

The AI Gateway Everyone Uses Just Got Backdoored: LiteLLM and the Healthcare Supply Chain Risk

LiteLLM, the Python library with 95 million monthly downloads powering nearly every AI agent framework, was compromised ...

Apr 20, 2026 14 min read
Read More
AI Security

UK Government Reality-Checks Claude Mythos: Why Healthcare's Cyber Basics Just Became Non-Negotiable

The UK AI Safety Institute's independent evaluation of Claude Mythos Preview reveals critical nuances missing from vendo...

Apr 19, 2026 8 min read
Read More
AI Security

Comment-and-Control: GitHub-Integrated AI Agents Vulnerable to Credential Theft

AI agents integrated with GitHub Actions can be hijacked via prompt injection to steal API keys and tokens. Anthropic, G...

Apr 16, 2026 7 min read
Read More
AI Industry Watch

VS Code 1.115.0 Brings Parallel AI Agents to Healthcare Development—With Security Built In

Microsoft's VS Code 1.115.0 introduces parallel AI agent sessions with worktree isolation, permission controls, and audi...

Apr 15, 2026 32 min read
Read More
AI Security

The Underground AI Threat Healthcare Isn't Prepared For: GTG-1002 and What Comes Next

While healthcare debated AI governance, adversaries built autonomous attack systems. GTG-1002—the first documented AI-or...

Apr 14, 2026 35 min read
Read More
AI Industry Watch

When AI Sells to AI in Healthcare: Why Patient Agents Will Reshape Medical Marketing

AI assistants are collapsing the patient journey into single conversations, and healthcare organizations aren't ready. W...

Apr 13, 2026 20 min read
Read More
AI Industry Watch

Why Anthropic's $500 Million Chip Bet Matters for Healthcare AI

Anthropic is exploring custom AI chip development as its revenue explodes from $9B to $30B in four months. The $500M inv...

Apr 10, 2026 20 min read
Read More
AI Security

Project Glasswing: When AI Finds Vulnerabilities Humans Missed for 27 Years

Anthropic's unreleased Claude Mythos Preview model found thousands of zero-day vulnerabilities across every major OS and...

Apr 08, 2026 23 min read
Read More
Previous
1 2 3 4 5 6 7 8 9 10 11
Next