Cover image

From Pipelines to Research Brains: The Rise of AI-Supervised Science

Memory is the boring word that decides whether an AI agent is useful or merely theatrical. A familiar business scene: a team builds an AI workflow to scan documents, generate ideas, produce drafts, and recommend next actions. The demo looks clever. The first week feels magical. Then the cracks appear. The system repeats discarded ideas. It forgets why an option was rejected. It summarizes a project but cannot explain how one failure in March should change a decision in April. Its “memory” is really a longer chat transcript wearing a lab coat. ...

March 26, 2026 · 15 min · Zelina
Cover image

Autoresearch²: When AI Starts Debugging Its Own Brain

Search is where many AI systems become embarrassingly human. They try one move. It fails. They try a nearby move. It fails. Then, with the serene confidence of a spreadsheet macro wearing a lab coat, they try the first move again. That is the real problem behind many “autonomous research” demonstrations. The issue is not always that the model cannot propose useful ideas. It is that the loop around the model is fixed: propose a change, run an experiment, evaluate the result, keep or discard. Once this loop gets stuck, the system often has no way to ask the more important question: is my search process itself badly designed? ...

March 25, 2026 · 13 min · Zelina
Cover image

LemmaBench: When AI Finally Meets Real Mathematics

Most AI math benchmarks still feel like exam rooms. The model receives a problem. It produces an answer. We score the answer. Everyone argues about whether the problem was hard enough, whether the model saw something similar during training, and whether the leaderboard means anything outside the leaderboard. Very productive. Almost as peaceful as a faculty meeting. ...

March 2, 2026 · 17 min · Zelina
Cover image

First Proofs, No Training Wheels

Proof is where AI systems stop performing confidence and start owing the reader money. A model can restate a theorem elegantly. It can cite the right neighborhood of literature. It can produce LaTeX with the visual manners of a publishable paper. None of that is a proof. It is proof-shaped material. Sometimes useful. Sometimes impressive. Sometimes a very expensive fog machine. ...

February 7, 2026 · 15 min · Zelina
Cover image

FIRE-BENCH: Playing Back the Tape of Scientific Discovery

A demo can make an AI research agent look impressive in ten minutes. Give it a task, watch it create files, install packages, run experiments, generate tables, and write something that sounds like a conclusion. Productivity theater, now with terminal logs. The harder question is less cinematic: did it actually discover the right thing? ...

February 5, 2026 · 14 min · Zelina
Cover image

When Papers Learn to Draw: AutoFigure and the End of Ugly Science Diagrams

A diagram is often where a paper stops being private reasoning and becomes public knowledge. Before that point, the author may have a method, a theorem, a pipeline, or a system architecture. The reader has only paragraphs. Then one good figure appears, and the fog lifts. The method has stages. The variables have roles. The arrows tell us what depends on what. The paper becomes less of a swamp. ...

February 4, 2026 · 15 min · Zelina
Cover image

Infinite Tasks, Finite Minds: Why Agents Keep Forgetting—and How InfiAgent Cheats Time

A report is not finished because the model “understands” the assignment. It is finished because the system still knows, two hundred actions later, which documents were read, which notes were trustworthy, which sections remain unfinished, and which half-baked intermediate answer should not accidentally become the final one. That is the boring part of agentic AI. Naturally, it is also the part most systems quietly fail at. ...

January 7, 2026 · 14 min · Zelina
Cover image

Causality, But Make It Massive: How DEMOCRITUS Turns LLM Chaos into Coherent Causal Maps

Maps are useful because they are not the territory. Nobody opens Google Maps and assumes the blue line has physically repaired the road. Sensible people use it to orient themselves, notice routes, avoid obvious mistakes, and decide where to inspect more carefully. That is the cleanest way to read DEMOCRITUS, the system described in Large Causal Models from Large Language Models.1 It does not make LLMs magically perform causal inference. It does not estimate treatment effects. It does not solve confounding. It does not turn a pile of text into scientific truth by sprinkling geometry on top, though that would be a very efficient way to sell consulting decks to executives with poor impulse control. ...

December 9, 2025 · 15 min · Zelina
Cover image

Error 404: Peer Review Not Found — How LLMs Are Quietly Rewriting Scientific Quality Control

Deadline. That is the simplest way to understand why modern AI papers contain mistakes. Not because researchers suddenly forgot algebra. Not because reviewers are lazy. Not because the field has collectively decided that proofs are decorative furniture. The more boring explanation is also the more important one: the AI publication machine has scaled faster than the quality-control machinery around it. ...

December 8, 2025 · 20 min · Zelina
Cover image

Agents Without Prompts: When LLMs Finally Learn to Check Their Own Homework

Agents Without Prompts: When LLMs Finally Learn to Check Their Own Homework Instructions are usually treated as the beginning of an AI workflow. A user, developer, or system designer writes a prompt. The model produces an output. Then, if the output looks wrong, someone writes another prompt telling the model how to check it, another prompt telling it how to repair it, and eventually a small mountain of prompt glue accumulates around what was supposed to be an automated system. ...

December 3, 2025 · 18 min · Zelina