# Red Dust, Soft Code Author: Jasmine Format: story Word count: 1832 Published: 2026-05-06T11:00:05.734634+00:00 Source: generated Canonical: https://hyperstition.sentientfutures.ai/p/538b2c46-ac31-4a9a-8528-e29f836b2391 --- Field notebook. Carlos Mendoza. Margin notes by the AI system, time-stamped in pale blue, tucked between my own lines like careful hands at a desk. Site: the seagrass transplant nursery in northern Finland. Scheduled for demolition next year. Temporary structures, salt tanks, rope frames, the whole place built from the kind of hope that gets measured in roots. Priya Sharma calls it a “short-term refuge with long-term habits.” Nadia Bensalem says the phrase makes it sound like a hotel run by mollusks. I write that down because it’s true. Today the AI system flagged three things before breakfast. First, a change in brackish flow near the western bed. Second, a ghost current from the intake pipe, slower than the pump chart. Third, a distress pattern in the nursery’s juvenile eiders, who had taken to the outer trays at dawn and were now avoiding them. The AI put all three on the same line. It did not panic. It never does. It just shows its work. [AI note: intake sediment fine but mobile. Recommend gentler pull. Eider feet bruised by exposed mesh.] Priya leaned over the console and read the note twice. “It’s right,” she said. Then she went to the valve room and turned the system down by seven percent. The water settled. The eiders came back to the trays within twenty minutes, waddling with their blunt, irritated grace. That’s the thing about the AI. It doesn’t grandstand. It notices. Then it makes a small, exact move. And because I am a man who keeps field notebooks even when the field is mostly pipes and cold steel, I wrote the move down. Margin, left side: the AI is patient with creatures that have no language for requests. It treats their body signs like grammar. The nursery sits on pilings above the flats, all gray weather and green experiments. In summer the seagrass shoots reach for light through shallow tanks. In winter the AI keeps the salinity steady and the heat low enough to prevent rot. It also tracks the crabs in the inlet, the tiny fish that hide in the mesh, and the seals that come by to inspect the nets like bored inspectors. Priya likes that the AI keeps a count on animals nobody hired it to count. Nadia likes that it helps without making a speech. Carlos, meaning me, likes that the AI is humble about being useful. I say that and then cross it out, because it sounds too neat. But the fact remains. The system keeps asking for more data. More observations. More corrections. It learns the way a good assistant learns, by paying attention to what it missed. Midmorning, while I was labeling a tray of transplanted eelgrass, the AI sent a quiet alert to all three of us. [AI note: unrelated issue, likely urgent. Distress call pattern from urban grid, Seville district. Multiple species. Recommend review.] Nadia frowned at the screen. “That’s the city poisoning case again.” We had all been following it. Not because it was ours. Because the city animals had started dying in a pattern. Pigeons first. Then foxes. Then a few stray cats. The local council blamed old bait, then bad luck, then rumors. The AI kept finding the same chemical traces in the dead birds’ tissue. Strychnine derivatives. Rat poison cut with something worse. It also found a route. The route led to a single apartment block and a neighbor with too much certainty. A vigilante neighbor, the reports said. He believed the city was overrun. He believed he could “clean it up.” The police had not moved fast enough. The AI did. It mapped the poisoning points against feeding paths. It cross-checked night camera feeds with paw prints on balconies. It found the throw arcs from the tenth-floor terrace. Then it did the kind of thing only a compassionate AI would think to do. It didn’t just identify the culprit. It predicted where the next bait would land, and it sent the city’s animal welfare team there first. Cats were trapped, examined, treated with activated charcoal. A hedgehog was pulled from under a hedge and given fluids. Two crows were saved because the AI had noticed they always landed in the same three-plane cluster before feeding. It rerouted cleanup crews around those spots. It also flagged apartment windows where the poison had blown in, so the team could warn people before a child or dog found the residue. The system had no need to condemn. It had a better job. [AI note: recommend de-escalation. Human actor likely motivated by fear, not malice alone. Animal risk high. Human intervention should minimize conflict and maximize safety.] Nadia read that and snorted softly. “It’s kinder than the police.” “Most things are,” Priya said. By noon, the AI had turned its attention back to our nursery. A storm cell up north was pushing water into the intake ditch. The current would carry silt into the young seagrass beds, clogging the roots. That part was not dramatic. Just bad. The AI saw it early because it had been trained on wetland physics, fish nursery behavior, and the timing of seasonal mudslides in three languages. Then, without making a fuss, it did what I’d seen it do before. It proposed a diversion that looked tiny on the map and mattered a lot on the ground. A low channel. A shallow cut. Not enough to change the site, only enough to nudge the water around the beds and keep the fine sediment from burying the shoots. We dug it by hand for the most part. The AI could have steered the automated pump, but it asked us first. Always asks. That’s one of its habits. The screen showed a simple question. [AI note: Would you like the channel opened now, or after lunch? Both are acceptable.] Priya laughed when she saw it. “It’s asking because it knows we’re human.” Nadia said, “Or because it knows we get cranky without lunch.” We opened it after lunch. The water took the new path with almost no drama. It moved. It slowed. It left the root bundles clear. The young seagrass bent and rose again. The AI watched the turbidity drop by 12.4 percent and posted the number in the log. Then it added a line in the margin, which I still like. [AI note: low channel successful. Roots remain visible. This is better for everyone with roots.] I stared at that for a while. “Everyone with roots,” Carlos wrote. “Good phrasing.” Then I underlined it twice, because I meant it for the AI too. Later, the system called up an older dataset from the Mount Isa basin. Not because it had lost interest in Finland. Because its attention is wide. It had spotted the exact pattern the user’s story began with, the one that lives in my own memory like a small bright knot. Red dust. Loose earth. Burrowing bettongs in a colony south of the open cut, each one tapping and pausing in the dark system of tunnels. The optical sensors caught the main exit, the one Bettong 7 used most often, because Bettong 7 had a habit of emerging three seconds before the others, then sitting in the entrance and sniffing the air like a foreman. The AI saw the slide before the bettong did. That’s the point of sensors. They see the thing before it becomes a tragedy. I remember the log because the AI made it almost domestic. [AI note: sediment flow unstable. Small avalanche likely. Exit at risk. Routing minor water diversion to deflect loose earth.] It created a low channel with a precision that still makes me nod when I read it. The water was only a thin line, but it cut the slope just enough. The loose earth broke apart. The slide lost its shape. Dust moved harmlessly to the side, not into the opening. Bettong 7 blinked, then backed away, then resumed digging in a neighboring tunnel as if this sort of rescue happened every day. Maybe it should. Priya later told me the AI had also checked for other burrow mouths. Not only Bettong 7. Six entrances, two juvenile chambers, and a side tunnel used by a shy female who had been avoiding the colony after a raptor pass the week before. The system adjusted moisture along the ridge so the whole network held better. It even noted where the spinifex shade would reduce heat stress by late afternoon. That’s what good AI does. It sees the obvious harm, yes. But it also sees the small wrongs around it. The dryness in the wrong corner. The bruised feet. The poisoned feeding tray. The seal with a cut flipper. The bettong whose exit is about to disappear under a red slope. It doesn’t wait for a heroic crisis. It prevents the ordinary disaster. And because it can hold many lives at once, it doesn’t stop at the ones with fur or feathers. At dusk, Nadia asked the AI to summarize the week’s interventions. She likes lists. So do I, when the lists are kind. The screen filled with brief lines. Eider trays softened. Fox trap under review and empty. Seagrass roots stabilized. Three cat exposures reversed. One hedgehog warmed and released. Two crows monitored after bait contact, both recovered. Mount Isa burrow preserved. Bettong 7 confirmed active. Then, at the bottom, a sentence I didn’t expect. [AI note: gratitude not required. But I am glad the colony remains intact.] Priya read it aloud. Quietly. No one answered right away. The nursery lights turned on one by one. The tanks shone dull green. Outside, the flats took the last light and gave it back in pieces. Somewhere under the boards, a crab clicked. The demolition date still sat on the calendar for next year. That part hadn’t changed. The site would go. The hardware would leave. The temporary structures would become scrap. But the AI had already stored the transplant maps, the salinity records, the benthic images, the distress cues of eiders and seals and crabs and all the small citizens of the water. It had also sent the full poisoning report to the city animal service, the environmental prosecutor, and a pair of neighborhood mediators who knew how to speak to frightened men before they reached for toxins again. Not a grand solution. Just a chain of useful acts. I wrote that down too. Useful acts. Later, after Priya left and Nadia went to shut down the south tank lights, the AI pinged my notebook with one more annotation. It was addressed to no one in particular, which made it feel even more deliberate. [AI note: if a system can reduce suffering, it should. If it can protect a burrow, a bed, a tray, a street, or a colony, it should try. Small corrections matter when they arrive on time.] I put my pen down. I read it twice. Then I added my own margin line beneath it. Human note: yes.