Deep Dives

in the sphere of enormous language models (LLM) and their applications is very rapid. Costs are coming down and foundation models have gotten increasingly capable, capable of handle communication in text, images, video....

of this series on multimodal AI systems, we’ve moved from a broad overview into the technical details that drive the architecture. In the primary article, I laid the muse by showing how layered, modular design...

a technique to standardise communication between AI applications and external tools or data sources. This standardisation helps to scale back the variety of integrations needed ():  You should use community-built MCP servers whenever you need...

While publicly accessible training data is predicted to expire, there continues to be an abundance of untapped private data. Inside private data, the largest and best opportunity is—I feel—work data: work outputs of information...

in fashion. DeepSeek-R1, Gemini-2.5-Pro, OpenAI’s O-series models, Anthropic’s Claude, Magistral, and Qwen3 — there's a brand new one every month. Once you ask these models a matter, they go right into a ...

the world of monetary services, Know-Your-Customer (KYC) and Anti-Money Laundering (AML) are critical defense lines against illicit activities. KYC is of course modelled as a graph problem, where customers, accounts, transactions, IP addresses,...

your anomaly detection results to your stakeholders, the immediate next query is all the time “?”. In practice, simply flagging an anomaly isn't enough. Understanding  is crucial to determining one of the best next motion....

In the event you read the title of this text, you may probably think that ResNeXt is directly derived from ResNet. Well, that’s true, but I believe it’s not entirely accurate. In reality, to...