Lightning Jar - Web Studio Lightning Jar Wordmark

Study X · Sessions & memory

"Undo that" needs an echo, not a transcript

Edit-anaphora

Study Overview

The Last Unmeasured Class

The last structurally unmeasured request class: follow-ups that point at the previous edit; "also set that same node's…", "apply the same change to X", "actually, undo that." Anaphora steps ran against skeleton views (an oracle-focused view would leak the answer), so the carrier under test had to supply the target, the key, AND the value.

No Carrier, No Chance

Without one, no model resolves anything: 0 of 144 across sonnet, gemini, and opus, and every single failure was a valid, applied, silently guessed patch; the strongest silent-failure result in the series.

The Echo Wins

Full history is near-ceiling (48/48, 48/48, 46/48). The winner is the cheapest carrier tested: a one-line last-edit echo the application appends automatically (set "key" from old to new on node), which ties history per model at about half the input cost and BEAT history outright on opus-4.8; 48/48 against history's 46/48, with the from/to format carrying every undo on every model.

Fine Print

Fine print, disclosed: "apply the same change to X" strains compressed carriers model-dependently (sonnet 7/12 with the echo; window-2 leaks on repeat everywhere, significantly on gemini), one more entry in the carrier-advice-is-not-model-independent ledger.

The Stack, Complete

The measured stateless session stack is now complete: fresh view per turn, two worked examples, the session-notes memo, and the last-edit echo.


Charts & Tables

Chart X.1: Anaphora Resolution by Carrier and Model


Table X.1: Anaphora success by carrier, kind, and model, with failure anatomy and cost