Everyone Has an AI Policy. Almost Nobody Has Evidence.
AI assurance is becoming the pentest of the AI era. What it is, why it matters for anyone shipping AI into production, and what an honest one looks like.
ai-assurancellm-securityevals
All Posts
Complete archive of our research, insights, and updates. Filter by topic or search to find what you need.
Filter by topic
13 posts (page 1 of 2)
The bench and the judge. Local stack to keep AI psychologically safe.
Open-source pscyhology safety toolset for conversational AI
keido-labsproductnews
AIPsyBench - the way to keep AI conversations safe
open-source pscyhology safety toolset for conversational AI
keido-labsproductnews
What happens when you strip a language model of its feelings
A 9D Lesion Study in Emotional Subspace in Transformers
ai-psychologyinterpretabilitynews
Whether, Not Which. What happens inside LLM when it process emotions.
A Mechanistic Dissociation of Affect Reception and Emotion Categorization in LLMs
ai-psychologyinterpretabilitynews
Empathyc 1.3 Released
Empathyc 1.3 is live. And it's obsessed with safety and privacy.
keido-labsproductnews
We Built a Safety System, Not a Surveillance Tool
Why we made a decision, that made out life harder
keido-labssafetynews
They Found the Persona. They Haven't Found the Self. (Yet?)
A clinical psychologist reads Anthropic's Persona Selection Model
ai-psychologyanthropicself
The Model People Mourned Was the Dangerous One
A clinical study of Empathyc in GPT-4o and GPT-5 generations
ai-psychologyclinical-frameworkskeep4o
Why AI Needs Psychology (Not Just More Parameters)
Why understanding humans is the next frontier in AI, and why we're building the science to get there.
ai-psychologymission