A failure log is rarely polite. A cooling pipe ruptures. A control system fails. Temperature does not jump instantly; it climbs. A later inspection action records an unsafe reading. Somewhere in that sequence, someone asks the expensive question: what caused the threshold breach? The lazy answer is: the last event before the alarm. ...
The explanation worked in the notebook; then production happened A familiar enterprise AI story begins with a reassuring demo. A model produces a questionable prediction. Someone opens a notebook, runs SHAP, LIME, a saliency map, a concept attribution method, or whatever interpretability tool is currently fashionable enough to appear in slide decks. The plot looks plausible. The team nods. Compliance is told that explainability has been “implemented.” ...
A lab is full of reviews. A candidate molecule is screened, criticized, scored, filtered, re-ranked, re-tested, and then quietly abandoned because one property looked promising while three others looked inconvenient. Drug discovery has never lacked opinions. It has lacked a clean way to convert those opinions into a machine-readable optimization process. That is the useful point in MAC-AMP: A Closed-Loop Multi-Agent Collaboration System for Multi-Objective Antimicrobial Peptide Design.1 The paper is easy to misread as another “LLM designs molecules” story. That would be tidy, familiar, and slightly wrong. ...
Runway safety has an annoying habit of being concrete. A planner can describe an autonomous aircraft as “agentic.” A vendor can call its navigation stack “adaptive.” A slide deck can place “responsible AI” in a tasteful blue box. But during take-off, the question becomes much less poetic: is that object relevant, how much clearance does it need, and should the vehicle recompute its path now? ...
Temperature is a patient witness. A valve ruptures. A cooling system fails. A technician records a radiation reading. Minutes later, the core temperature crosses a danger threshold. The incident report now asks the question every system audit eventually asks, usually after everyone has already chosen a favorite suspect: Who caused the temperature rise? ...
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. ...
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. ...
Automation has a boring failure mode: the moment the world becomes slightly more complicated than the workflow diagram, the system starts asking for a human. That is not because the model lacks vocabulary. It is because the automation system does not know how to grow its own capabilities. Most AI agents are still built around a fixed menu of actions, fixed task definitions, and fixed reward signals. They can optimize, but they rarely expand the set of things they know how to optimize for. Very impressive, in the way a microwave is impressive until you ask it to cook without buttons. ...
A customer-service agent rebooks a flight, checks a policy, calls an API, updates the passenger record, apologizes politely, and still gets the outcome wrong. The old explainability question would be: which input tokens influenced the final answer? That question is not useless. It is just late to the crime scene. When an AI system only predicts, explanation can focus on a single input-output decision. When an AI system acts, explanation has to follow the behavior across time: the state it maintained, the tool it selected, the observations it received, the recovery move it attempted, and the point where the run quietly became unrecoverable. A nice feature-importance chart does not tell you that. It tells you what mattered to a prediction, not how a workflow failed. ...
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. ...