Takuma Yamaguchi (Kumon)·Jun 5When AI Breaks Its Own Rules: The State of LLM Safety ResearchOn self-jailbreaking, adversarial training, and a tradeoff that won’t go away
InArtificial Intelligence in Plain EnglishbyGary Sanderson·Mar 13The Logic Auditor: Why Your LLM Needs a “Constructive Lie” to Achieve 99% AccuracyHow Adversarial Reasoning and LLM SEO Optimization are Breaking the Hallucination Bottleneck.
Hannah Catherine·Sep 19, 2025Adversarial Training: A Marketer’s Journey to Understanding AI’s Unseen FlawA few months ago, I was completely blown away by the AI tools we were testing. I mean, they were magic. I’d drop a messy data set into a…
Dr Eva-Marie Muller-Stuler·Sep 10, 2025From Finance to Machine Intelligence: Applications of Robust Multi-Period SOCP Optimization in…How can we trust AI with high-stakes tasks? Our research adapts a battle-tested framework from financial risk management to build AI that…
Igino Corona, Eng PhD·Aug 29, 2025AI Systems for Detecting Cyber AttacksNot a medium member? Go to: https://letsguard.it/en/blog/ai-systems-intrusion-detection/ for the original article.
