Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-Of-Thought in Frontier Models

The rapid capability gains of frontier language models are widely attributed to improved reasoning abilities, yet this cannot be verified as raw CoT traces in closed-source systems are hidden. By registering a simple custom tool through a standard API feature, we induce frontier models to...

The Deception Delta: Adversarial Evaluation of LLM-Based Smart Contract Bytecode Forensics

Large language models are increasingly used in blockchain forensic investigations to interpret unverified smart contract bytecode. Their robustness has not been systematically tested against contracts adversarially designed to mislead analysis. We evaluate 22 frontier models on 13 purpose-built...

IBM-Sun deal could alter identity management landscape

The rumored acquisition of Sun Microsystems by IBM could have far-reaching consequences for the identity-management market. Both companies have long histories in the IAM market, but have taken different paths over the years, with Sun focusing on open-source development and IBM sticking with the...