Subscribe
Sign in
Home
Archive
About
Latest
Top
Discussions
What Security Evidence Survives a Model Swap?
Find which AI security claims survive a model swap and decide to reuse, renew, narrow, or retire each one, with the math and a register.
Nov 17
•
Rock Lambros
1
2
1
Weekly Musings Top 10 AI Security Wrapup: Issue 62: November 6 to November 12, 2026
AI agents found the bugs on about twenty approvals this week. The checking layer, from model weights to enclave builds to the triage queue, is now the…
Nov 13
•
Rock Lambros
2
1
3
Agentic AI Breach Containment: Who Signs Off on Killing Production?
GitBook went dark 15 hours to stop an attacker. RockCyber Musings shows why agentic AI breach containment hinges on the smallest identity you can…
Nov 10
•
Rock Lambros
1
3
1
Weekly Musings Top 10 AI Security Wrapup: Issue 61: October 30 to November 5, 2026
OpenAI's agents built Linux root exploits for about $1,280 apiece while AI platforms kept losing keys the old way. 11 verified AI security stories from…
Nov 6
•
Rock Lambros
1
2
2
Anthropic’s S-1 Prices Open-Weight Models. Its Red Team Tested One.
Anthropic S-1 open-weight models get filed as cheap. Its red team found GLM-5.3 near Mythos on exploits. Get the forecast and 4 things a CISO should do…
Nov 3
•
Rock Lambros
2
3
2
October 2026
Weekly Musings Top 10 AI Security Wrapup: Issue 60: October 23 to October 29, 2026
Fred Wilmot and I released the Context Bill of Materials at [un]prompted II, because the operator wrote 0.10% of what the model read. Eleven verified AI…
Oct 30
•
Rock Lambros
1
1
1
Context Bill of Materials: A Record of What Your AI Agent Read
See what your AI agent read. The Context Bill of Materials signs MCP tool definitions and records each inference it builds. Open source.
Oct 27
•
Rock Lambros
1
Weekly Musings Top 10 AI Security Wrapup: Issue 59: October 16 to October 22, 2026
A CA key equal to 4, a PHP embargo that leaked before the patch, and a LiteLLM release poisoned behind the latest tag. Eleven verified AI security…
Oct 23
•
Rock Lambros
1
1
1
AI Evaluation Security Needs a Bypass Certificate
AI evaluation security failed at four frontier labs. Get process safety's bypass rules, proof test math, and a six-field certificate.
Oct 20
•
Rock Lambros
1
1
1
Weekly Musings Top 10 AI Security Wrapup: Issue 58: October 9 to October 15, 2026
The FTC and Brussels asked the labs for their records, Bank of America paid for Mythos in contractors, and Anthropic pulled its own internet. 11…
Oct 16
•
Rock Lambros
1
1
1
AI Made Security the Bottleneck. Then the CFO Came for the Reviewers.
AI moved the bottleneck to the people who check its work, and the queue math shows what happens to everyone else when you cut one of them.
Oct 13
•
Rock Lambros
5
1
1
Weekly Musings Top 10 AI Security Wrapup: Issue 57: October 2 to October 8, 2026
Agent Session Logs, The Identity Gap, And The Week A Vendor Said Injection Is Not A Bug
Oct 9
•
Rock Lambros
2
1
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts