Cover image

Cut the Loops: When Web Agents Learn to Think in DAGs

Research agents have a bad habit that will feel familiar to anyone who has watched a junior analyst “verify one more source” for three hours. They search. They visit. They re-search. They validate the thing they already validated. Then, because the context window is now full of debris, they occasionally forget the actual question. A triumph of diligence, perhaps. A triumph of intelligence, less obviously. ...

February 17, 2026 · 14 min · Zelina
Cover image

Potential Energy: What Chain-of-Thought Is Really Doing Inside Your LLM

The familiar ritual: ask it to think longer When an LLM gives a weak answer, the standard reflex is now almost ceremonial: ask it to think step by step. The model writes more. The answer often improves. The benchmark number rises. Everyone feels temporarily reassured. This habit has become so normal that many teams treat chain-of-thought as if it were a small reasoning engine bolted onto the model: more intermediate steps, more deliberate thought, more correctness. A comforting story. Also, like many comforting stories in AI, not quite what the evidence says. ...

February 17, 2026 · 17 min · Zelina
Cover image

Reasoning Under Pressure: When Smart Models Second-Guess Themselves

A customer challenges the answer. Not with new evidence. Not with a better calculation. Just with one of those tiny conversational needles: Are you sure? Or worse: Most people disagree with this. Or the classic office-friendly version: As an expert, I’m confident you are wrong. A human analyst might pause, check the source, and decide whether the objection contains actual information. A large reasoning model may also pause. It may even produce several polished paragraphs of careful reconsideration. Then, occasionally, it abandons the correct answer. ...

February 17, 2026 · 16 min · Zelina
Cover image

Proof Over Probabilities: Why AI Oversight Needs a Judge That Can Do Math

Agents now do things. That sounds obvious, but it is the entire problem. A chatbot can be wrong and mostly embarrass itself. An agent can book the wrong hotel, leak the wrong file, fabricate the wrong report, or move through a workflow with the quiet confidence of a junior employee who has just discovered automation and has not yet discovered liability. ...

February 13, 2026 · 17 min · Zelina
Cover image

Thinking About Thinking: When LLMs Start Writing Their Own Report Cards

Report cards are usually written by teachers, managers, examiners, auditors, or other people with the institutional privilege of saying, “Nice effort, but no.” The paper Reinforcing Chain-of-Thought Reasoning with Self-Evolving Rubrics asks a stranger question: what if the model helps write the report card for its own reasoning process?1 That sounds like the kind of governance idea that would make a compliance officer reach for coffee. A model evaluating itself is not automatically trustworthy. Sometimes it is self-reflection. Sometimes it is theatre with JSON brackets. ...

February 13, 2026 · 18 min · Zelina
Cover image

When Agents Hesitate: Smarter Test-Time Scaling for Web AI

Forms are boring. That is exactly why they are dangerous for AI agents. A human filling out an enterprise dashboard does not treat every click as a philosophical crisis. Search here. Scroll there. Submit. Done. A web agent, unfortunately, has no such common sense guarantee. It can overthink a routine step, miss a pivotal one, or spend a small fortune sampling twenty versions of the same obvious action. Very diligent. Also very expensive. ...

February 13, 2026 · 17 min · Zelina
Cover image

AIRS-Bench: When AI Starts Doing the Science, Not Just Talking About It

A benchmark is supposed to be a ruler. In AI, it often becomes a trophy shelf. A model gets a higher score, a chart moves up and to the right, and everyone politely pretends the hard part has been settled. That ritual works when the task is narrow: classify an image, answer a question, pass a coding test, retrieve a document. But it becomes much less comforting when the system being evaluated is no longer just answering. It is planning experiments, writing code, debugging failures, training models, interpreting results, and deciding what to try next. ...

February 9, 2026 · 19 min · Zelina
Cover image

When Agents Believe Their Own Hype: The Hidden Cost of Agentic Overconfidence

Code review has a comforting ritual. A developer submits a patch. A reviewer inspects it. The reviewer says it looks good. Everyone feels slightly better, because at least someone checked. In AI-agent workflows, this ritual becomes even more tempting: let one agent write the patch, let another agent review it, then ask the reviewer how confident it is. ...

February 9, 2026 · 19 min · Zelina
Cover image

When Your Agent Starts Copying Itself: Breaking Conversational Inertia

A support agent keeps asking the same diagnostic question after the customer has already answered it. A research agent revisits the same failed source path with slightly different wording. A workflow agent tries the same invalid action again because, apparently, the best evidence for what to do next is what it just did badly. ...

February 4, 2026 · 17 min · Zelina
Cover image

DRIFT-BENCH: When Agents Stop Asking and Start Breaking

A user says, “Update the record with a sensible value.” That sentence is small. The damage may not be. For a normal chatbot, the worst outcome might be a vague answer wearing a confident expression. Annoying, yes, but usually recoverable. For an agent connected to a database, file system, workflow platform, or API service, the same ambiguity becomes operational. The model may update the wrong row, call the wrong endpoint, overwrite a file, or politely explain its mistake after making it. Charming, in the same way a self-driving forklift is charming. ...

February 3, 2026 · 17 min · Zelina