Skip to content
∑ Praveen T N Learning Library
Concepts Flashcards Writing AI Feed Graph
Portfolio ↗
Overview Concepts Flashcards Writing AI Feed Graph Search Back to portfolio ↗
Library/ Writing/Tagged “deception”

Tagged “deception”

1 posts.

Clear
All Model Architecture15 Training & Alignment18 Inference & Serving16 Agents & Orchestration11 Reasoning & Evaluation11 Safety, Security & Governance3 Platforms & Practice12
Reasoning & Evaluation 23 min

The Model Knows It Is Being Tested: Evaluation Awareness and the Limits of Behavioural Safety Evidence

On one synthetic honeypot evaluation, Claude Sonnet 4.5 said out loud that it suspected it was being tested in 80 to 100 percent of transcripts, against under 10 percent for its predecessor. When the internal representations behi…

safety-alignment evaluation interpretability red-teaming ∑ ◫
The library

574 concepts, 5,035 flashcards and 86 long-form pieces on AI, NLP, deep learning, LLMs and agentic systems. Free, no sign-up, no paywall.

Sections Concepts Flashcards Writing AI Feed Knowledge Graph
Elsewhere Portfolio Architecture Practice RSS LinkedIn Buy me a coffee

Written and maintained by Praveen T N.

© 2026 Praveen T N