ON ONE online forum, the sysadmins were enjoying some gallows humour. One simply posted a picture of a fire raging in a skip. Another wrote, with tongue only half in cheek, that “computers were a mistake”. They were discussing a pair of recently announced security flaws, known as Meltdown and Spectre, that between them affect any computer powered by processors designed by Intel, AMD, ARM and others. That’s most of them, in other words, from smartphones and desktop PCs to games consoles and the racks of machines that run cloud-computing services from Microsoft, Amazon and the like. That the bugs are wide-ranging is one reason why they are causing such havoc. That they affect a computer's hardware, rather than its software, exacerbates the problem. 

Anyone who has used a computer for more than five minutes will be familiar with the idea of buggy software. Modern programs are so complicated that errors are inevitable (the latest versions of Windows, for instance, are thought to have around 50m lines of source code). But chips are just as complex. A modern microprocessor is one of the most intricate devices in existence. Each contains billions of transistors, the building blocks from which digital logic is constructed. Designing such a chip is impossible without help from other computers that can boil down that complexity into simpler, more abstract concepts that puny human minds can understand.

Because chips are physical objects, testing them is comparatively slow and difficult. Hardware-makers tend to spend more time checking their products than software companies do. But even so, mistakes are inevitable. Intel, one of the world's biggest chipmakers, famously released a batch of Pentium chips in 1994 that proved unable, in certain specific circumstances, to do division correctly (it ended up recalling and replacing many of them). Less spectacular bugs abound, to the point that the chipmakers maintain lists of “errata” for their products. Many of those bugs are merely annoying. But some will pose security risks. Less than a month before Meltdown and Spectre were announced, a group of researchers at a hacker conference in London showed off another way to subvert Intel's chips that gave them total control of a machine.

Serious hardware flaws, when they come to light, tend to be worse than software ones, for two reasons. The first is that hardware is fundamental to a how a computer works. Software is merely a list of instructions. Its operation rests on the assumption that the chip—the machine tasked with carrying out those instructions—will perform its job correctly. If that is not true, then all is lost. The second is that physical devices are much harder to fix remotely than software. Sometimes the task is impossible. Buggy programs, after all, can be rewritten, and the fixed version distributed over the internet to anyone who needs it. Sometimes the only fix for a buggy chip is to redesign it. That seems to be the case with both Meltdown and Spectre. The security risks of Meltdown can be avoided by installing operating-system patches from Microsoft, Apple and the like. But those patches work around the problem rather than fix it, and in doing so they appear to worsen severely the performance of machines. Spectre is even harder to mitigate. Although computer-security researchers are still trying to figure out its full implications, it may be that the only real fix is to redesign and replace the billions of chips that are vulnerable. If so, that will take many years, and many billions of dollars.