Browsing: Editor’s Picks

If you work in product or tech, you have probably sat through this meeting. Someone forwards a vendor demo or a viral post, and suddenly the roadmap needs an agent, an MCP app, or a harness. We see the same scene in client meetings all the time, usually starting with “we need an agent for…

This time last year, I released a Deeplearning.ai course with Andrew Ng on Governing AI agents with the goal of educating developers on the basics of data protection for effective and responsible agent deployment. The motivation for the course came from IBM’s 2025 breach study, which found 97% of the organizations that suffered an AI-related…

Not every modelcall needs to generate text. Routing is often a small decision hidden inside a large agentic system, yet many systems ask a decoder language model to generate that choice token by token.

Modern AI coding agents can implement a specification and produce a passing test suite in the same workflow. The problem is that both the code and the tests come from the same reading of the same ambiguous sentences, which means the tests cannot disagree with the implementation. This breaks the core rule that makes Verification…

There’s a category error that shows up in many LLM systems: We retrieve a few documents, put them in context, generate a fluent answer with links, and then we call the answer “grounded.”

In a previous article, we saw why training with MSE forces a model to report only the conditional mean, and howGaussian NLL lets it learn an honest per-step uncertainty σ sigma as well. That was the one-step story. This post picks up where that left off.

I built the whole thing in pure Python and ran the tests myself, with the results shown as pass or fail.

Most AI applications do not always need another paragraph of generated text. Sometimes they just need a decision.

Benjamin Nweke described a failure that took him three weeks to notice. He had turned on Structured Outputs for a pipeline that parsed payment confirmation messages into transaction records, and his reconciliation job started flagging a small, steady stream of mismatches — a couple of percent of a week’s volume. Not crashes. Not malformed rows.…

Retrieval-augmented generation (RAG) answers questions using information retrievedfrom a set of documents. That document collection is called a corpus. A typical evaluationsends a well-written question to a tidy corpusand checks whether the retriever returns the correctpassage.