The check — how a model decides.
An AI picks its next word the way a VAR checks a goal: weigh every clue, then commit.
Check three goals and watch the VAR weigh the evidence — then see what happens when the clues disagree.
When a goal is scored but something looks off, the referee sends it to the VAR — the video assistant — who studies the replays. Offside? Over the line? A hand in the build-up? No single clue settles it, so the VAR weighs several at once: the offside line, goal-line technology, the handball check, and the build-up replay.
The VAR weighs them all together and always reaches a call — GOAL or NO GOAL — confident when the clues agree, only just leaning one way when they don't. (A real VAR can leave it to the on-field decision; a language model can't — it always answers.)
A large language model (or LLM) decides the same way, only its call is a single word. Given the text so far, it puts odds on every word that could come next and commits to one, then repeats for the word after that. The same instinct as the VAR, one word at a time.
You hand over the inputs. The VAR decides.
You don't write the weighing — you assemble the evidence and ask. The VAR weighs it with an eye shaped by seasons of football, and hands back a call, along with the odds it put on that call.
# Hand the VAR the evidence — you don't code the weighing. decision = var.review( offside="level — onside", goal_line="ball fully over", handball="no arm contact", build_up="clean move", ) # decision.call → "GOAL" · decision.confidence → 0.96
Weigh everything, commit to one call.
Three finishes, three different bundles of evidence. The offside line alone didn't decide it — the VAR weighed it against the goal-line read, the handball check, and the build-up, and always committed: a confident call when they agreed, a barely-there one when they didn't. It never left the decision unmade.
An LLM chooses its next word the same way. It weighs the words so far, puts odds on every candidate, and commits to one — sure when the odds pile onto a front-runner, only just when they're split. Then it repeats, word after word.