Glean and Foretell
FEATURES + PREDICTION — *the clues you pick are the only thing the guess can reason from: choose the clues, and you shape the guess.*
Loading audio…
Press play to listen along. The line being read lights up as you go.
Show full transcript
Loading transcript…
Glean the magpie and Foretell the tree frog work the two ends of one job. Glean stands at the near end, over a pile of clues, keeping a few and dropping the rest. Foretell sits at the far end, on the tip of his branch, taking whatever clues she hands him and leaping — guessing about something brand new. What passes between them is a small bundle of chosen clues, and what comes out the far end is a guess. And here is the thing they both know in their bones: the guess can only ever be as good as the clues.
"I pick what the machine gets to look at," Glean says, patting her satchel. "And I make the guess from only that," Foretell says, tapping his empty spyglass. "Whatever you don't hand me, I never even know was there." "So if I hand you junk," Glean says. "Then my very best leap," Foretell finishes, "lands in the mud."
Glean does the choosing. She spreads a heap of clues about a photo across her end of the bench: the animal's ears, its tail, its size, the background, the time of day the photo was taken, the name of the file. "Watch me sort," she says. "Ears — keep, that's really about the animal. Tail — keep. Background snow — drop it, that's a trap, it's about the weather, not the creature. File name — drop it, that's about the photographer." She sweeps the traps off the bench and ties the keepers — ears, tail, size — into a tidy bundle. "These three carry the real signal," she says. "Not what sits near the answer. What causes it." She slides the little bundle down the bench toward the frog. "Now it's Foretell's leap — but notice, he can only leap on what I chose to keep."
Foretell does the leaping. He takes Glean's bundle and points his empty spyglass at a photo the machine has truly never seen. "From ears, tail, size," he murmurs, "my guess: a fox. And here's my reason — pointed ears, bushy tail, small. You can check it." He beams. "See? A guess, with the clues showing, so anyone can look. That's an honest leap." Then he sets the good bundle down and, just to show the danger, picks up a different bundle — one where someone slipped the snow-background clue back in. He leaps again. "From snow-in-the-picture… my guess: wolf." He shakes his head. "Same me. Same leap. But fed the trap clue, my best guess is nonsense — it's guessing the weather, not the animal. I didn't get dumber. I got fed worse."
Then a real test came, and it showed exactly how the two of them make or break a guess together. A tool was meant to guess whether a plant was sick. Someone had let it grab every clue lying around — leaf color, leaf spots, and the little plastic label that happened to say "greenhouse 4," where all the sick plants had come from. Glean caught it first. "That label isn't about the plant," she said. "It's about where it was standing. Drop it." Foretell nodded hard. "Because if you leave it in and I leap on it, I'll just learn 'greenhouse 4 means sick' — and the day a healthy plant comes from greenhouse 4, I'll call it sick, confidently, for no real reason." So they did it right, as a pair: Glean stripped the bundle down to the clues that were truly about the plant — the color, the spots, the droop — and only then did Foretell leap, guessing "sick, because of the yellowing and the spots, here's my reason, you can check it." The guess came out sharp and honest — but only because her choosing and his leaping had happened in the right order, each trusting the other. "A guess," they said almost together, "is a leap. And a leap is only as true as the ground you leap from — and the ground," Glean added, "is the clues I hand him."
"So a good guess starts way before the guess," a kid said slowly. "It starts with what someone chose to notice?"
"That's the secret of it," Glean said, and Foretell nearly fell off his branch nodding. She tied one more clean bundle; he made one more honest leap; and together they set the finished guess — clues and all, reasons showing — down in the middle of the bench. Under the quiet, the two of them felt the same calm settle: not the sinking feeling of a clever leap wasted on junk clues, not the itch of a pile too big and untrue, but a light, paired, well-built gladness — the ease of a magpie who kept only what was true and a frog who leapt only on what was true, so that between them a guess came out both bold and honest. That right-order, well-fed, leap-from-solid-ground feeling, steadier than any lucky guess built on a trap, was to Glean and Foretell exactly why they worked the two ends of one bench, and trusted what passed between.
The NeuralQuest ensemble
Glean and Foretell is part of NeuralQuest's distributed-narrative cast. Each character embodies a different curricular primitive; together they teach the full subject.
-
Tag
Labeling — the cheerful labeler who treats every label as a human choice and meaning-making act ('every label is a choice — and you're the one making it')
-
Drill
Training loops — the focused practitioner who treats iteration as rhythm, not race; explicit teacher of when-to-stop ('once, again, again — different this time? Then again')
-
Skew
Bias + data fairness — the bias-vigilance anchor who always asks 'whose data is in here, whose is missing, who decided'; appears in every kit from kit 5 onward
-
Veer
Generalization vs overfit — the wandering scout who treats generalization as travel ('trained here, tested here — now go somewhere new, does it still know the way?')
-
Weigh
Ethics + decisions — the reflective elder who carries the ethics gate at the AI-in-society capstone ('can we build it? Yes. Should we? That's a different question')
-
Foretell
Prediction — the model learned on the past; now it guesses about something it's never seen (the leap is the whole point and the whole risk)
-
Glean
Feature selection — a computer can't look at everything; what you let it look at is what it learns from, so choose the clues on purpose
-
Odds
Confidence — I'm not sure, I'm 80% sure; those are different, and the difference is the whole point
-
Rue
Loss — how far off was that guess? the exact size of the miss tells the model which way to change
-
Verge
Decision threshold — the model gives a number, I draw the line; move the line and you choose what you'd rather be wrong about
