Notes from the review queue
Practical writing on evaluating, governing and living with AI systems, from people who have to sign for them.
RAG Eval Sets: The Secret to a Reliable AI Product
Imagine an AI system advising a doctor on treatment protocols or summarizing a patient’s medical history. A single hallucinated fact could be disastrous. This is why Retrieval-Augmented Generation (RAG) is essential: it anchors the LLM to a verified knowledge source (like internal clinical guidelines or legal documents), ensuring the answer is accurate, up-to-date, and fully […]
Read the full post →Non-Determinism: Why it is a Feature, not a Bug, in LLMs. Plus, what Thinking Machines Lab’s quest for consistent output mean for Responsible AI.
If you have ever asked an LLM the same question twice and received different answers, you have experienced non-determinism. While this might seem like a bug, it is actually a fundamental characteristic of these powerful models. To understand why, let’s contrast it with a more traditional, deterministic system. Determinism vs. Non-Determinism: A Personal Story As […]
Read the full post →Unpacking AI Accountability
In traditional software development, accountability is relatively straightforward. A bug in a program can often be traced back to a specific line of code or a developer’s oversight. The responsibility is clear. AI, as we know it now, introduces the “black box” problem. The model’s decisions are based on patterns learned from vast datasets. This […]
Read the full post →Humanizing AI
Conversations with the academics, authors, and practitioners shaping how AI gets governed. Hosted by Cesar Koirala.