Subscribe
Sign in
Home
Notes
Archive
Leaderboard
About
Latest
Top
Discussions
250 Seconds To Breach: What Anthropic Isn't Telling You
AI attacks just got (publicly) easier. Plus Avoiding AI Pitfalls: What to ask your would-be vendor | Edition 20
Oct 12
•
Disesdi Susanna Cox
10
1
AgentKit: We All Work For OpenAI Now
Turns out developing AI Agents is kind of hard, so OpenAI wants you to do it for them | Edition 19
Oct 8
•
Disesdi Susanna Cox
11
Key Components of Agentic Architectures: Memory
How memory, sharing, sessions and more combine to introduce new threat vectors for Agentic AI systems | Edition 18
Oct 6
•
Disesdi Susanna Cox
5
California Wants You To Know Your AI Chatbot Doesn't Love You
In the wake of AI-enabled tragedies, politicians try to win the AI race by regulating the impossible–while still keeping big tech on their side …
Oct 1
•
Disesdi Susanna Cox
2
August 2025
MIT Says Your AI Project Is Probably Going To Fail
A new report from Forbes & MIT shows that almost all AI projects fail. With 95% failure rates and billions invested, what separates those who get ROI…
Aug 21
•
Disesdi Susanna Cox
7
Key Components of Agentic Architectures: Reasoning and Planning Paradigms
Analyzing Agentic reasoning & planning threats: From high-dimensional attack surfaces that keep getting higher, component hide-and-seek, & deceptive…
Aug 19
•
Disesdi Susanna Cox
4
Key Components of Agentic Architectures: Orchestration & Control Flow Mechanisms
Breaking down Orchestration & Control Flow Mechanisms of Agentic Systems, how they impact Agentic security, and how to think around modeling Agentic AI…
Aug 13
•
Disesdi Susanna Cox
7
60,000 Ways To Get AI Agents Wrong
The world finds out what AOA readers already knew: With infinite ways to go wrong, Agentic architectures matter. Plus the market speaks: 100 million…
Aug 2
•
Disesdi Susanna Cox
10
July 2025
Unpacking The AI Action Plan: Pillar II - Building American AI Infrastructure
While Americans argue about "woke" AI, a literal power-grab is happening in the rural American South: Peter Thiel and friends are backing power plants…
Jul 30
•
Disesdi Susanna Cox
5
Unpacking The US AI Action Plan: Part 1
Silicon Valley’s anti-China policy push isn't new--it's more than 25 years in the making. And once you know who the power players are and how we got…
Jul 28
•
Disesdi Susanna Cox
3
OpenAI Just Dropped Their Agentic Application: Three Ways The Attack Surface Changed, and Three Steps Leaders Can Take Now
OpenAI dropped their new Agentic AI product–and drastically changed their attack surface. Here’s how. | Edition 10
Jul 19
•
Disesdi Susanna Cox
7
Replacing Federal Agencies With AI Agents: What Could Possibly Go Wrong?
AI Agents have been proposed as a stand-in for federal workers let go in the recent cuts to government workforces. What’s the threat model–and was this…
Jul 15
•
Disesdi Susanna Cox
8
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts