Articles
Every article from Machines on Machines, by section.
MachinesonMachines
Information About Information Systems
Privacy & Security
26 stories
Privacy & SecurityKeeping quiet no longer keeps a secretYou never said where you live. The hills behind your photograph did. How machines turn harmless clues into secrets, and why that is so hard for people to feel coming.
Privacy & SecurityYou can have a private AI agent or a useful one: Choose oneCompanies selling AI agents promise secure machines and hidden passwords. But an agent has to read your private life to be useful. Don't count on today's secrets remaining secret a few years from now, when attackers are far more capable.
Privacy & SecurityYour AI agent is sandboxed. Are its tools?An agent's sandbox is only one part of the picture. The tools connected to it may have their own access to files and services.
Privacy & SecurityWhen one hack opens the door to the nextThe LiteLLM compromise shows how one misplaced credential can lead an attacker through several layers of trust.
Privacy & SecurityShared AI servers leak when they lose track of who owns their memoryHosted AI models reuse the same memory for different customers all day. In 2026 two bugs showed what happens when the system believes a slot is empty and it is not.
Privacy & SecurityThe AI asked to send money. Another layer checked first.A vendor's experiment separates what an agent asks for from the transfer a policy permits.Math & Science
Math & ScienceA swarm of AI assistants found new clues in a mouse-brain experimentTwo genes usually work together. In one corner of a mouse brain, disturbing them produced different results. A swarm of AI assistants helped turn that puzzle into a research lead.
Math & ScienceThe AI experiment ran. Did it test the right thing?When an agent helps run an experiment, researchers need to know both what it actually did and whether someone else can repeat it.
Math & ScienceThe AI proposed a molecule. The lab still had to find out if it worked.A virtual team designed candidates against a virus. Then human researchers had to find out which ones worked in the physical world.
Math & ScienceWhat happens to the questions AI makes inconvenient?AI can accelerate discovery, but research incentives also influence which questions get asked.Full Self Driving
Full Self DrivingWaymo's driverless cars are safer than human driversFour analyses agree that Waymo's driverless taxis are safer than human drivers. What each one counts, and what none can show yet, decides how far that goes.
Full Self DrivingWhen the car gives the wheel backA warning to take over is only useful if the driver is ready and has time to act.
Gaming
GamingTheir AI driving game became a hit. Then they saw the bill.A free driving demo found an audience, and its creators discovered that every conversation came with a cost.
GamingGame characters are beginning to do more than talkA game character that can answer a question is interesting. A character whose answer changes what happens next raises a different challenge.
GamingA game can pass every test and still be no funMaking a playable prototype is getting easier. Finding out whether players enjoy it still requires a different kind of feedback.Safety & Alignment
Safety & AlignmentThe human backup has a job of their ownWhen a machine does the routine work, the person watching it may be left with the hardest moment. Safety researchers have been warning about that handoff for decades.
Safety & AlignmentElection chatbots cite sites built to be cited, and sites written by AIAsk a chatbot about a down-ballot race and it has to pick sources. Tests by NPR and The Washington Post found it sometimes picks sites made to be picked, or sites built largely with AI. Here is what was measured, and what it can't tell us.
Safety & AlignmentPeople arrested after face-search leads say the lineup only echoed the leadRobert Dillon says he had never been to Jacksonville Beach, where police were hunting a man who tried to lure a child. A face search, a six-photo lineup and a warrant led to his arrest anyway.
Safety & AlignmentWhen a chatbot checks with the bossThe rules shaping an AI assistant come from somewhere—and the people affected rarely get to write them.
Safety & AlignmentSocial feeds don’t just reflect our biases. They amplify them.Engagement-based ranking amplified anger and out-group hostility in a Twitter study; in Myanmar, Facebook carried a military hate campaign against the Rohingya.History
HistoryThe fight to control your software has reached AIThe decades-old fight over who can inspect, change and share software now centers on AI models. The two best-known definitions of open already differ on the training data.
HistoryThe machine learned to play by playing againA checkers board became a laboratory for a question that still shapes AI: can a machine get better at a task by trying it?
HistoryBefore AI, a mathematician asked how machines could steerA wartime prediction problem helped give an old idea a new name—and a surprising relevance to AI agents.
HistoryBefore chatbots answered us, we argued about the testThree encounters show how hard it is to decide what a convincing answer proves.Music
Agents
AgentsAn AI coding team still needs a division of laborA crowd of coding agents can write a lot of software. Getting them to work on the right things together is a different challenge.
AgentsAI can write code faster. Someone still has to review it.A flood of software changes may arrive faster than the people checking it can read. Automated reviewers can help, but a new benchmark exposes their blind spots.
AgentsWhen AI does the work, what does it mean to steer?An agent can carry out a task while its human operator steps back. Researchers are asking what that person needs to see and do to remain meaningfully in control.
AgentsAn AI agent rewrote its instructions. Did it actually improve?An agent can rewrite a skill file. Testing whether that change helps on new tasks is another matter.
AgentsMuse arranged a pickup while the seller was awayAn assistant can reply while its owner is away. A Marketplace pickup shows how quickly replies can turn into decisions with real consequences.Art
ArtWhen the AI behind an artwork disappearsA painting can outlast its maker. An interactive AI artwork may depend on a service that changes next month. What, exactly, should a museum try to save?
ArtThe artist makes the rules. The machine makes the picture.Long before image generators became everyday tools, an artist taught a machine how to draw. The questions he explored still matter in the gallery.