The Threat Prompt Newsletter
Subscribe
Sign in
Home
Archive
About
Prompt Injection, End of 2025: Progress, Without the Self-Deception
Agentic AI will reward organizations that are honest about the risks they are taking — and intentional about where they are willing to take them.
Dec 24, 2025
•
Craig Balding
Latest
Top
Discussions
Overconfident by Design
When AI Outputs Mask Data Shortfalls
Nov 23, 2025
•
Craig Balding
1
1
LLM Agents: Delegate the Work, Not the Understanding
On the importance of owning the mental model when deploying LLM agents in real systems
Nov 16, 2025
•
Craig Balding
1
1
Human-in-the-Loop Is Just the Starting Line
A practical approach to scaling intelligent automation - without losing control
Nov 1, 2025
•
Craig Balding
1
LLMs Found the Code You Forgot Was There
CVE-2025-10230: remotely exploitable bug in Samba
Oct 17, 2025
•
Craig Balding
1
Reader Question: Can LLMs really reason?
This is a topical and important question for cyber.
Jun 14, 2025
•
Craig Balding
1
Before You Deploy an AI Threat Detector, Send This Email
Before deploying that “AI-powered threat detector” your vendor is promoting, pause to consider a key risk: a single tainted data source can flood SOC…
Jun 1, 2025
•
Craig Balding
Create Better Security Visuals with AI
Spotting AI-generated security images is easy: padlocks, shields, jumbled words, and that distinctive “AI look”; they rarely look decent.
Mar 27, 2025
•
Craig Balding
See all
The Threat Prompt Newsletter
Get Daily AI Cybersecurity Tips
Subscribe
Recommendations
Last Week in AI
Last Week in AI
Simon Willison’s Newsletter
Simon Willison
Growthstore.xyz
Sri and Ramesh
The M&Ms Newsletter
Louie Bacaj
The Threat Prompt Newsletter
Subscribe
About
Archive
Recommendations
Sitemap
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts