A Blind Review Read the Visual Effects in My Explainer Short as Factual Claims

← hexisteme · notes · 2026-11-13

Adversarial reviews of the effect plans for two explainer shorts kept reading visual effects as factual claims, such as a PHOTO label on a synthetic cleaning reading as forged evidence. I fixed only the effects that read opposite to the facts, refused requests to cut effects, and left b05, where two reviews disagreed, to a human.

On 2026-11-09 I sent the effect plans for two explainer shorts out for adversarial review, one about a famous painting and one about a mountain park. Codex reviewed both; agy also attacked the painting short, and Gemini read the mountain short's script in an earlier round. Many of the findings had the same shape: this effect, as drawn, states something that is not true.

A gray wash on a forest reads as "the forest died." A PHOTO label on a synthetic cleaning animation reads as a forged photograph. Fireworks read as a celebration that someone recorded. None of these effects were meant as statements. The reviewers read them as statements, and in each case I checked the reading against the sources before deciding.

This note is about how I sorted those findings, which ones I refused, the one line I left to a human because the two reviews pointed in opposite directions, and the rule that came out of it.

Why the effects were there at all

Some context on why the plans were full of effects. I had complained repeatedly, across channels, that my shorts had no reactions in them: "I need you to look at each line of the script carefully and mix in suitable effects, and there are none." On November 8 that became a written rule for all my shorts: every line gets at least one event where something on screen physically changes, stickers alone don't count (stickers at most 40 % of events), and feedback like "more effects" is never converted into a cap. Caps are soft fatigue warnings only; the floor is the contract.

My main Claude session also wrote a diagnosis of why the same complaint kept coming back. The existing gate only measured whether something changed: mean brightness difference inside the event box at least 4/255, a sound effect present for every change, and a width check of at least 7 %. In the diagnosis's words, nobody judged whether the effect matched the meaning, or whether it was big enough to react to, or overdone. There was also no step where effects were chosen. They were hand-coded line by line during the build, so the repertoire collapsed to moves, palette cards, color fills and sweeps. The diagnosis's fix was an effect plan written after the script freezes and before the build: for each line, the emotional beat, the image the words call up, the on-screen effect, the sound and the size. Then a check, then an adversarial review by Codex and agy, then measurement after render against the plan.

So by the time the reviews ran, the plans were deliberately dense. That matters for what I did with the findings.

What the reviewers flagged

The painting short's round 1 came back Codex FAIL/FAIL and agy FAIL/FAIL. Many of the script findings were ordinary: too many words for the length limit, a tangent outside the sources, an overclaim like "everyone thought." The effect findings are the ones this note is about. Here they are from the triage table, with what replaced them:

Each of these is an effect saying something the script did not say. The reviewers did not object to the effects being loud. They objected to what they asserted.

Some of these findings turned into checks on the plan itself. Each effect row now must state what it teaches. A row with photo status must carry evidence, a source id or a real file, and its motion is limited to comparison and zoom. An IMAGINE marker must have a size_px of at least 48, because a one-pixel chip technically labels the effect as imagined while nobody can see it. Text effects need text_px of at least 54 and dur_s of at least 1.5, so a label cannot flash past. One finding I did not turn into code: agy caught narration saying "up" while the screen showed the feet. That stays an item for adversarial review and eye checks.

The blind round, and the criterion

The mountain short went through more rounds. For round 3, Codex got a blind sheet generated from the reactions file: each line's dialogue and on-screen events, with the viewer's inner thoughts and the roles masked. One Codex run, verdict FAIL.

The criterion I applied was: fix only the places that read opposite to the facts. Findings of the "cut the effects down" kind would not be adopted, because they contradicted my own instruction (effects and sound on every line) and the rule that feedback is never turned into a cap.

That criterion sorted the round cleanly in most places.

Adopted, two findings:

Rejected on the facts, three findings:

Rejected by rule: the remaining lines, b01–b04, b06–b08 and b12, where the findings asked to remove or soften effects and sounds (the radius figure, a cow emoji, a hiss, a blackout, a tilt). Audibility is measured separately on a phone band instead of being argued about in review.

Held for a human, two findings:

I did not pick a side on b05. My criterion says fix what reads opposite to the facts; one reviewer says the current effect does, the previous reviewer said the previous effect failed for another reason, and the narration already carries a label. That is a judgment call, so it went to a human with both readings attached.

The two adopted fixes went into the same build, build 7. I did not record a pass for the script stage. The blind pass for the final contract is decided by human review.

The same failure in the words

The effect findings had a twin in the script reviews. In the mountain short's round 1, Gemini offered a rewrite of one line that opened with the Crown confiscating the land first, as the step toward marking out the boundary. It reads smoothly, and it is a causal claim: that the confiscation happened in order to mark the boundary. The sources do not say that, so I rejected it. Gemini's other suggestion on that line, replacing "the Crown" with "the government" because the term is unfamiliar, I adopted.

An effect that turns gray and a sentence that adds "in order to" fail the same way. Each adds a cause or an outcome the sources don't contain, and the viewer has no way to tell it was decoration.

What became a rule

Rule 3 of the reactions rule now reads, in short: effects follow the meaning of the line. The example is a line about firing at an atomic nucleus: the glow, the steam sound and the mushroom cloud happen inside a thought balloon, and the balloon pops on the next line. Alarm staging for a wrong guess (red heat, steam, smoke, clouds, warning lights) stays inside the imagination balloon only. Put it in the real scene and the false causation survives even after the narration says "it wasn't." The rule cites an adversarial review round 3 from that same day (11-09) as its origin.

The last sentence of that rule is the lesson of the round. An effect shown in the real scene is a claim about the real scene. A later line of narration can retract the words, but the image has already been shown as if it happened.

Rule 6 is the limit on all of this. Fun cannot be measured by a machine. What gets recorded is a blind script review, with inner thoughts and roles masked, and silent and sound-on viewings of the animatic. A gate PASS is never reported as a verdict on whether a short is fun. Nothing in this note says the shorts got better to watch. The reviews told me where effects asserted something false; they did not tell me whether anyone enjoyed them.

What is still open

b05 and b09 are with a human, and I have no outcome to report for either. The criterion "fix only what reads opposite to the facts" depends on a reviewer noticing the misreading in the first place, and round 3 was one Codex run; I do not know what a second blind reviewer would have flagged on the same sheet. The checks I added (teaches, evidence, marker size) make a plan state its claims, but whether a stated claim matches what a viewer reads still comes from review and eye checks, not from the checker.

FAQ

What kind of effect did the reviewers flag as a false claim?

Examples from the painting short: a synthetic cleaning animation with a PHOTO marker read as forged evidence, fireworks and cheering read as a documented celebration, and a BANNED chain on the canvas read as the painting itself being banned. In the mountain short's blind round, the circle going ash-gray to show excluded land read as the forest dying.

Why were requests to cut down the effects rejected?

My own instruction required effects and sound on every line, and my reactions rule says feedback is never converted into a cap; caps are soft fatigue warnings only and the floor is the contract. So in round 3 the criterion was to fix only places that read opposite to the facts, and the findings on b01–b04, b06–b08 and b12 asking to remove effects were rejected. Audibility is measured separately on a phone band.

What happened when two reviews disagreed on the same line?

On b05, Codex read the returning forest color as a forest created or recovered in 1881, while Gemini in round 2 had asked for that forest color because the earlier cream fill hid the contrast. A FOREST RESERVE · 6-mile radius note already appears on that word. I did not pick a side and held the line for a human decision.

What rule came out of these reviews?

Rule 3 of the reactions rule: effects follow the meaning of the line, and alarm staging for a wrong guess (red heat, steam, smoke, clouds, warning lights) stays inside an imagination balloon. Put in the real scene, the false causation survives even after the narration says it wasn't so.

Does passing the effect checks mean the short is fun?

No. Rule 6 says fun cannot be measured by a machine. What gets recorded is a blind script review with inner thoughts and roles masked, plus silent and sound-on animatic viewings, and a gate PASS is never reported as a verdict on fun.

Related notes

Fixed your problem? Good — that's the whole point of this page. Every note on this site is free to read. I write one of these up whenever I hit a failure worth recording: agent-fleet operations, harness bugs, and the measurement that proved the fix. The email list for these notes — no issue has gone out yet, so you would be on it before the first one.
← hexisteme · notes · about · editorial policy · privacy · contact · CC-BY 4.0