7 Common Misconceptions When Choosing an AI Model
Token price, benchmark scores, model size, and context windows can all be misleading. Here are seven common model-selection misconceptions—and the real-world examples that challenge them.
Sreenivas Makam's Blog
AI infrastructure, cloud platforms, and distributed systems.
Latest posts
Why We Built Model Academy: Understanding How AI Models Produce Answers
We created Model Academy to connect concepts that are often taught separately—model weights, inference systems, and GPU execution. This is the story behind the academy, our complementary perspectives, and why we chose an interactive approach to explain how AI models produce answers.
AI in CI Should Not Replace Your Tools. It Should Read the Evidence.
Deterministic CI tools should produce the evidence. AI should generate targeted probes, interpret the combined results, and help the human reviewer decide where to focus.
AI Code Review in CI: Codex Cloud vs GitHub Actions vs CodeRabbit
I tested three AI code review approaches on the same pull request defects to understand what each option gives you, what you must build yourself, and where the real tradeoffs are.
Constrain, Adapt, Evaluate: Rethinking Coding Assessments for the AI Era
AI-native coding assessments should not ban AI or allow unlimited delegation. SignalLoop explores a third model: constrain collaboration, adapt assessments at the role level, and evaluate the engineering process through evidence.
Prescribed Enterprise AI Architectures for Small, Mid-Size, and Large Organizations
The first article in this series, Enterprise AI Adoption: Requirements for Security, Governance, and Scale, defined the problem: enterprises consume AI through coding tools, standalone hosted applications, custom agents, and enterprise knowledge systems, but need consistent controls across identity, credentials, data, cost, providers, and operations. The second article, A Reference Architecture…
A Reference Architecture for Governed Enterprise AI
In the first article in this series, Enterprise AI Adoption: Requirements for Security, Governance, and Scale, we identified four ways enterprises consume AI and seven requirements that apply across them. Those requirements cover identity, non-human credentials, cost governance, security and data controls, model flexibility, optimization, and observability. This article translates those…
Enterprise AI Adoption: Requirements for Security, Governance, and Scale
AI adoption inside enterprises rarely begins with a coordinated platform strategy. It usually starts with individuals and teams selecting tools that solve immediate problems. A developer subscribes to an AI coding assistant. Another team builds an application using a foundation-model API. Employees begin using standalone cloud applications such as ChatGPT, Claude, Gemini, or Codex. A … Continue…
VLAs Are Winning. World Models Will Win.
A perspective from the data layer of humanoid robot training I recently spent time working on egocentric video data — first-person footage of humans doing everyday things with their hands — and how it could be used to train humanoid robots. It’s a narrow problem, but it forced me to answer a bigger question: what … Continue reading VLAs Are Winning. World Models Will Win. →
AI Assistants Have Many Interfaces. Context Is the Real Product.
AI assistants are no longer just chat windows. The same assistant now appears as a web app, desktop app, mobile app, browser extension, IDE extension, command-line tool, local agent, and cloud worker. That is powerful, but it creates a new problem: deciding which interface to use, and keeping context alive when moving between them. This … Continue reading AI Assistants Have Many Interfaces.…