Arnab’s expertise lies in providing solutions to complex problems in the area of IT Security. He has 23+ years of experience in leadership roles at large organizations like British Telecom, Tech Mahindra, iViZ (part of Synopsys), Metric Stream, Capgemini, IBM & more. Arnab was one of the key members to have worked in the BT21CN, one of the largest transformation projects in the telecom world aimed at the complete transformation of BT’s telecom network to Next Generation Network (NGN).
Many objections to belief-state planning are framed as concerns about scalability. In practice, they are concerned about visibility. Systems that avoid explicit belief do not eliminate uncertainty; they merely conceal it. This concealment can appear efficient, but it comes at a cost that is paid later often at the point where decisions matter most. This… Read More »Combinatorial Belief States Are the Cost of Explicit Uncertainty
For most of the past decade, the trajectory of large language model research followed a familiar arc: scale up the compute, widen the data, tune the alignment, ship the product. Each new generation of models arrived with modestly improved benchmark scores, better instruction-following, and marginally reduced hallucination rates. Opus replaced Sonnet. Sonnet replaced Haiku. The… Read More »Demystifying Claude Mythos Preview: The Model That Changed Cybersecurity Forever
This article is a continuation of Why LLMs Are Not Planning Machines. In that earlier post, the core claim was simple: large language models can generate plausible action sequences, but they do not plan. They lack a mechanism to reason over uncertainty across time. This follow-up post focuses on what is missing. The missing abstraction is the… Read More »Belief State: Why AI Planning Fails Without It
In the course of my work with LLMs, I’ve been examining a recurring pattern in how large language models are being used inside real systems. In many settings, I observed that LLMs are treated as planners where they are used to generate multi-step workflows, remediation strategies, operational playbooks, and even “autonomous” action sequences. These plans… Read More »Why LLMs Are Not Planning Machines (And What It Means)
FireCompass Research has published a new IEEE TecRxiv paper examining a technical weakness increasingly visible in autonomous cybersecurity systems built around large language models. The work, Belief-State Engine: Augmenting LLMs for Principled Planning Under Partial Observability, was authored by two members of the FireCompass research team, including FireCompass co-founder and Head of Research, Arnab Chattopadhayay. … Read More »(IEEE) Belief-State Engines: Solving Uncertainty in Autonomous Security Systems