Subscribe • Previous Issues A Better Way to Build and Refine Agents Modern AI applications have evolved far beyond single models. Many systems orchestrate multiple specialized agents — planners that decompose tasks, extractors that gather data, generators that create content — all coordinating through external tools and APIs. This architectural shift creates a fundamental optimization problem: theContinue reading “Beyond RL: A New Paradigm for Agent Optimization”
Category Archives: Uncategorized
A Tiered Approach to AI: The New Playbook for Agents and Workflows
A Small Language Model (SLM) is a neural model defined by its low parameter count, typically in the single-digit to low-tens of billions. These models trade broad, general-purpose capability for significant gains in efficiency, cost, and privacy, making them ideal for specialized tasks. While I’ve been cautiously testing SLMs, their practical value is becoming clearer.Continue reading “A Tiered Approach to AI: The New Playbook for Agents and Workflows”
Top 10 Open-Source Projects in the Large Model Ecosystem
This leaderboard ranks the ten most influential open-source projects in the AI development ecosystem using OpenRank, a metric that measures community collaboration rather than simple popularity indicators like stars. The list spans the entire technology stack, from foundational infrastructure such as PyTorch for training and Ray for distributed compute, to high-performance inference engines like vLLM,Continue reading “Top 10 Open-Source Projects in the Large Model Ecosystem”
Is your LLM overkill?
Subscribe • Previous Issues A Tiered Approach to AI: The New Playbook for Agents and Workflows A Small Language Model (SLM) is a neural model defined by its low parameter count, typically in the single-digit to low-tens of billions. These models trade broad, general-purpose capability for significant gains in efficiency, cost, and privacy, making them ideal forContinue reading “Is your LLM overkill?”
Rethinking Databases for the Age of Autonomous Agents
As the AI community buzzes with the potential of autonomous agents, I’ve been pondering a less glamorous but critical question: what does this mean for our data infrastructure? We are designing intelligent, autonomous systems on top of databases built for predictable, human-driven interactions. What happens when software that writes software also provisions and manages itsContinue reading “Rethinking Databases for the Age of Autonomous Agents”
Why Your Database Can’t Handle the Coming Agent Swarm
Subscribe • Previous Issues Rethinking Databases for the Age of Autonomous Agents As the AI community buzzes with the potential of autonomous agents, I’ve been pondering a less glamorous but critical question: what does this mean for our data infrastructure? We are designing intelligent, autonomous systems on top of databases built for predictable, human-driven interactions. What happensContinue reading “Why Your Database Can’t Handle the Coming Agent Swarm”
The Enterprise Search Reality Check
Before the AI hype cycle exploded with ChatGPT in late 2022, I was focused on a less glamorous, but equally important shift: the resurgence of enterprise search. Neural retrieval and vector embeddings finally looked practical. After the release of ChatGPT, an assumption among some AI teams was that these powerful new models would solve theContinue reading “The Enterprise Search Reality Check”
A pragmatic guide to enterprise search that works
Subscribe • Previous Issues The Enterprise Search Reality Check Before the AI hype cycle exploded with ChatGPT in late 2022, I was focused on a less glamorous, but equally important shift: the resurgence of enterprise search. Neural retrieval and vector embeddings finally looked practical. After the release of ChatGPT, an assumption among some AI teams was thatContinue reading “A pragmatic guide to enterprise search that works”
Foundation Models in Robotics: From Bespoke Machines to Generalist Brains
I’ve been reading a great deal about modern manufacturing, an industry where robotics has been a central figure for decades. For all their success in the structured environment of a factory, these robots have struggled to break out of their cages and into more dynamic, general-purpose roles. This situation is not without precedent; for thoseContinue reading “Foundation Models in Robotics: From Bespoke Machines to Generalist Brains”
Robotics Is Becoming AI’s Ultimate Testing Ground
Subscribe • Previous Issues Foundation Models in Robotics: From Bespoke Machines to Generalist Brains I’ve been reading a great deal about modern manufacturing, an industry where robotics has been a central figure for decades. For all their success in the structured environment of a factory, these robots have struggled to break out of their cages and intoContinue reading “Robotics Is Becoming AI’s Ultimate Testing Ground”