We have all been there: packed shoulder to shoulder on the train while the person beside us coughs and sneezes. A protective flu jab offers some reassurance, but so does the thought that there will be a hospital bed for you, should you need it. Yet, in England, about 95% of adult hospital beds were occupied at the height of flu season last year. If hospitals were hotels, that level of occupancy would be good business, and we would commend them for their efficiency. But do we really want a hospital to have so few beds in reserve that it’s just one bad flu week away from having to treat patients in corridors?
This is the subtle thing about efficiency. We usually assume that more of it must be better. But we can become so focused on improving one thing that we lose sight of the others. You can try to arrange your calendar so that every minute is accounted for, but you’ll soon start running over and end up behind. A gap between meetings might seem like inefficiency, but it’s what allows your schedule to recover when something unexpected happens.
Mathematicians have a name for the pursuit of efficiency. We call it optimisation. Give us something to minimise or maximise – cost, time, fuel, profit – and we will try to find the best possible answer. For most of human history, people optimised by common sense. But computers have enormously expanded what can be effectively tackled, from airline schedules to supply chains. The gains for society have been extraordinary. But there are at least three traps to beware of in the relentless pursuit of optimality.
The hospital bed story illustrated the first one: weakening a system’s robustness by squeezing out too much slack. An empty bed can be redundant on a quiet Tuesday night, but it’s somewhere precious to put the next patient when flu cases surge. If you judge a system by its performance under ordinary conditions, you can lose the ability to cope with extraordinarily challenging ones.
A second trap is having a too-narrow definition of “best”. Take the city of Milton Keynes. Designed by urban planners in the late 1960s, it has an American-style grid system. As the city began to be built out, roundabouts rather than traffic lights became a defining feature of its road junctions; today there are about 130 of them. The roundabouts were great for traffic flow, but they came with a now-notorious cost. Have you ever taken the coach from Oxford to Cambridge? An hour in, you get great views of Milton Keynes, but a busload of queasy passengers, as the coach negotiates one roundabout after another. Slow down, swing left, curve right, accelerate. It’s hard to appreciate the seamless merging of vehicles when your stomach is churning.
Traffic flow is important, to be sure. Engineers find it convenient to optimise because it’s relatively easy to measure. Passenger comfort, on the other hand, is harder to quantify. In a case like this, #optimisation gives you the best answer to the question you asked, but can deliver unwelcome answers.
[AgentUpdate Depth Analysis] The efficiency trap offers profound lessons for the AI Agent ecosystem. Current frameworks like LangChain, CrewAI, and AutoGen pursue extreme optimisation of task completion efficiency, often neglecting system #robustness and interpretability. Just like hospital beds, an Agent system that over-optimises response speed or resource utilisation may collapse under edge cases. For instance, in multi-agent collaboration, over-optimising communication efficiency can lead to loss of critical information; in tool invocation, over-optimising call counts may sacrifice accuracy. In the future, Agent design needs to introduce the concept of "elastic slack" to balance efficiency and robustness. Meanwhile, optimisation objectives must not be limited to task completion rates but should also include user trust, safety, and maintainability. Horizontally, OpenAI's Agent framework emphasises generality, while Anthropic's MCP protocol stresses standardisation of tool calls, but both face similar traps. The long-term healthy development of the Agent ecosystem requires a shift from "efficiency first" to "resilience first"—perhaps the key to avoiding the hospital's fate.
