Ashish Kharbanda·4d agoMechanistic Interpretability of LLM Refusal BehaviourWhere does a language model keep its “refusals”?A response icon1A response icon1
Shayan Bemanian·Oct 27Reading LLMs Minds — Natural Language Autoencoders ExplainedHow can you train a neural network to translate activations into English when nobody knows what the activations mean in the first place?
Alborz Nazari·Oct 19Your Firewall Can’t Read English: What Linux and Windows Hardening Get Right, and Where It Breaks…1. The claim and its premises
Pancham_B·Sep 15Building model_probe: An Open-Source Framework for Adversarial Safety Testing of LLMsI recently released model_probe v0.1.0 (https://github.com/panchambanerjee/model_probe), an open-source Python framework for adversarial…
InLunit Team BlogbyCedric Caruzzo·Jul 20Deceptive Grounding: Entity Attribution Failure in Clinical Retrieval-Augmented GenerationTL;DR. We found a failure mode in clinical retrieval-augmented generation (RAG) that is invisible to every standard check. The model…
Jim Walker·Jul 13The Golden Rule: Never Give AI More Access Than You Can Recover From🧠 The AI Mindset: Keep Your Hands on the Wheel
Shubham Lagad·Jun 22Does quantization quietly change an LLM’s safety? Help me find out.The gap nobody checks
Subash Niroula·Jun 21Directory-Scoped PII Firewall for Claude Code AgentsPart 2 of 6 in a series on treating your AI coding agent like infrastructure.
Mikel·Jun 11LLM Hacking: A Practical Guide to Safe Data Annotation in Research.Avoid systematic error and validate your LLM-annotated findings with these evidence-based strategies
InSystem WeaknessbyBerend Watchus·Apr 29ROBOTICS: The “Linguistic Trap”: Why Solo LLMs are a Chain of Accidents Waiting to HappenAuthor: Berend Watchus Independent non-profit AI & Cybersecurity Researcher. April 29, 2026 [Publication for System Weakness, online…
