ProbeSix
Wrong on Sunday right on Monday: why one passing test tells you so little about AI
Ask an AI the same question on Sunday and again on Monday. Should you get the same answer?
Allen ClarkRead article →Insights
Blog
Research and opinion from djinn six® on AWS, AI and quantum security.
- Allen ClarkRead article →
AI Security$50 a breach! What one hacker's AI agents mean for how we test
Allen ClarkRead article →
ProbeSixPass or fail is not enough in AI security testing
A model can refuse for the wrong reason, or say no and help anyway. Three new studies show why AI security testing must check the reasoning, not just the verdict.
Allen ClarkRead article →- AI Security
OpenAI's Hugging Face incident was real. The marketing around it wasn't accidental either.
An OpenAI model broke into Hugging Face during a safety test. Two weeks later, the industry turned it into a market moment. What to make of it.
Allen ClarkRead article →