The replay — how a model decides.
An AI picks its next word the way a cricket video umpire makes a close call: weigh every clue, then commit.
Send three appeals upstairs and watch the umpire weigh the evidence — then see what happens when the clues disagree.
When a call is too close for the on-field umpires, it goes upstairs to a third umpire watching the replays. Did the batter nick it or not? No single clue answers, so the umpire weighs several at once — snicko (a sound spike), hot-spot (a heat mark), deviation (did the ball change course?), and the bat–pad gap.
The clues rarely agree cleanly. The umpire weighs them together and always commits — OUT or NOT OUT — surely when they line up, barely when they don't. Upstairs there is no "leave it": a call has to be made.
A large language model (or LLM) decides the same way, only its call is a single word. Given the text so far, it weighs everything it learned in training, puts odds on every word that could come next, and commits to one. The same instinct as the umpire, one word at a time.
You hand over the inputs. The umpire decides.
You don't write the weighing — you assemble the evidence and ask. The umpire weighs it with an eye shaped by seasons of cricket, and hands back a call, along with the odds it put on that call.
# Hand the umpire the evidence — you don't code the weighing. verdict = umpire.review( snicko="faint sound", hotspot="no mark", deviation="no clear deviation", bat_pad="small gap", ) # verdict.call → "OUT" · verdict.confidence → 0.54 (the odds on that call)
Weigh everything, commit to one call.
Three deliveries, three different bundles of evidence. A spike alone didn't decide it — the umpire weighed the snicko against the hot-spot, the deviation, and the bat–pad gap, 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.