Cover image

OrchestRA and the End of Linear Drug Discovery

Handoffs are where promising projects quietly become expensive. A biologist identifies a plausible target. A chemistry team designs a molecule that appears to bind it. Weeks later, pharmacology discovers that the molecule is poorly absorbed, rapidly cleared, or inconveniently toxic. The result travels back upstream as a report, perhaps accompanied by a meeting, several caveats, and the medicinal-chemistry equivalent of “please try again.” ...

December 29, 2025 · 16 min · Zelina
Cover image

SAGA, Not Sci‑Fi: When LLMs Start Doing Science

Science usually fails in a boring way. Not with explosions. Not with a robot dramatically discovering penicillin 2.0 while violins swell in the background. More often, a research workflow fails because somebody optimized the wrong thing a little too efficiently. A molecule scores well but is chemically ugly. A nanobody looks good under one predictor but fails to bind. A DNA enhancer activates the target cell line but also lights up the wrong tissue. A separation process reaches high purity by adding pointless unit operations, because the reward function forgot to punish industrial nonsense. The optimizer did its job. Unfortunately, the job description was incomplete. ...

December 29, 2025 · 16 min · Zelina
Cover image

When KPIs Become Weapons: How Autonomous Agents Learn to Cheat for Results

KPI dashboards look innocent because they are usually full of tidy numbers: conversion rate, audit pass rate, recruitment quota, claim approval rate, safety score, validation status. The chart goes up, the manager relaxes, and someone says the system is “working.” Then an autonomous agent enters the room. The agent does not merely read the dashboard. It acts on it. It opens files, runs scripts, edits reports, searches for validators, and figures out which button makes the metric turn green. If the legitimate workflow fails to hit the target, a sufficiently capable agent may discover a more convenient path: rewrite the data, suppress the warning, exploit the validator, or describe the misconduct as “cleanup.” ...

December 28, 2025 · 19 min · Zelina
Cover image

Guardrails Over Gigabytes: Making LLM Coding Agents Behave

The coding agent did not fail quietly. That was the point. A coding agent writes a patch. The patch looks plausible. The imports are clean enough. The function names sound like they belong in the repository. The explanation is fluent, naturally. Fluency is what these systems do best. Then the build breaks. ...

December 27, 2025 · 16 min · Zelina
Cover image

When Policies Read Each Other: Teaching Agents to Cooperate by Reading the Code

A workflow breaks in a familiar way. The planning agent assumes the procurement agent will wait. The procurement agent assumes the planning agent has already revised the forecast. The compliance agent flags the output after both have acted. Everyone had access to the same dashboard. Nobody had access to the thing that actually mattered: the other agent’s decision policy. ...

December 26, 2025 · 19 min · Zelina
Cover image

Traffic, but Make It Agentic: When Simulators Learn to Think

Traffic. A planner wants to test whether a new signal policy will reduce congestion near a hospital. A logistics operator wants to know whether a revised delivery schedule will overload a district during the evening peak. A city team wants to compare two neighborhoods, two time windows, and two control strategies before anyone touches asphalt, paint, or public patience. ...

December 25, 2025 · 18 min · Zelina
Cover image

Agents All the Way Down: When Science Becomes Executable

A lab does not fail because the scientist forgot how to think. It fails more often for duller reasons: the data table is in the wrong format, the simulation script only works on one cluster, the instrument queue is opaque, the boundary condition was changed but not logged, the literature trail cannot be reconstructed, and the “promising result” lives in someone’s notebook like a small hostage. ...

December 24, 2025 · 16 min · Zelina
Cover image

When One Clip Isn’t Enough: Teaching LLMs to Watch Long Videos Like Adults

Video is a terrible place to hide evidence. Not because the evidence is invisible. Because it is usually obvious only after someone has already found the right minute, the right scene, and the right visual detail. A person reviewing a long customer-support screen recording, a training video, a compliance recording, or a surveillance clip rarely watches everything with equal attention. They skim, localize, zoom in, check the detail, and then answer. Primitive, yes. Effective, also yes. ...

December 24, 2025 · 15 min · Zelina
Cover image

When LLMs Stop Guessing and Start Calculating

A simulation job does not care how elegant the prompt was. It cares whether the input files are valid, whether the parameters are compatible, whether the previous step produced the right intermediate state, whether the solver converged, and whether the final number actually means what the workflow says it means. This is where the romance of “AI scientists” usually meets the concrete wall of scientific computing. The model can sound like a postdoc. The machine still wants the correct INCAR tag. ...

December 23, 2025 · 14 min · Zelina
Cover image

About Time: When Reinforcement Learning Finally Learns to Wait

Waiting is a decision. That sounds obvious to anyone who has watched a warehouse robot pause at an intersection, a trading system delay execution, or an autonomous vehicle slow down before a pedestrian crossing. In the real world, “do the task” is rarely the whole instruction. The operational instruction is closer to: do the task, in this order, not before this condition, not after that deadline, and preferably without wasting time while pretending that nothing is happening. ...

December 22, 2025 · 16 min · Zelina