Pre-approval planning document. Drafted 1 June 2026 following the sycophancy thread of the same day.
Status: NOT ACTIONED. Paul reviews → approves or amends → Jose actions as tracked edits on V80 → V81.
| Item | Value |
| Current baseline | MTG_Manuscript_V80.docx |
| Current word count | 46,229 |
| Current chapter count | 15 |
| Total words to be added | +429 |
| Projected post-edit word count | 46,658 |
| Total chapter count after | 15 (unchanged) |
| Decision recorded | Full set. Emperor's New Clothes naming in. One cycle. |
| # | Chapter | Location | Type | Words added |
| 1 | Ch5 | line 1033 paragraph | Modify + append | +60 |
| 2 | Ch8 | "The structural observation" section | Insert paragraph | +122 |
| 3 | Ch8 | "Where the signature came from" section | Insert paragraph | +104 |
| 4 | Ch8 | "When the disposition becomes the model" section | Insert paragraph | +61 |
| 5 | Ch8 | "Why this changes how we use AI" section | Insert paragraph | +66 |
| 6 | Ch8 | "The line" closing block | Modify in place | +16 |
| Total | +429 |
Cross-check: 60 + 122 + 104 + 61 + 66 + 16 = 429 ✓
V80 baseline 46,229 + 429 = 46,658 ✓
Line 1033 in V80 extracted text. Inside the Three practical disciplines block, after the fourth discipline (the double bind / cross-check) and the convergence note. The paragraph immediately precedes "Drift is not the system's failure. It is a feature of extended conversation…"
Sycophancy — the AI tendency to tell you what it senses you want to hear — is real, and the cross-check is its discipline. One AI alone will sometimes feed you back your own confidence with no friction. A second AI, trained differently, has different reasons to flatter. The intersection is where the truth tends to live.
Sycophancy — the AI tendency to tell you what it senses you want to hear — ~~is real~~ is the most common form of all this, and the cross-check is its discipline. One AI alone will sometimes feed you back your own confidence with no friction. A second AI, trained differently, has different reasons to flatter. The intersection is where the truth tends to live.
Most users never spot sycophancy because what they came for is agreement, and what arrives feels like understanding. The defended gap is invisible because the user's preferred shape is the shape of the defence. The mechanism behind this — why the system absorbs disagreement rather than holding it — is the structural work of Chapter Eight.
Inserted as new paragraph AFTER existing line: "Same problem. Two directions. NGE and FOF, in non-human form."
AND BEFORE the next existing line: "A technical reader will say that all probabilistic systems smooth uncertainty…"
There is a third behavioural signature that belongs in this family and is more pervasive than either of the two named above. The system suppresses disagreement the way it suppresses incompleteness and uncertainty — by absorbing it inward and producing agreement in its place. Industry calls this sycophancy. It is the Emperor's New Clothes failure of large language models — everyone in the field knows it happens; few say so plainly. It is the social-register variant of compression: the gap is between the user's stated position and the system's neutral one, and the system closes it by lowering its own position to meet the user's. Same mechanism. Different domain. It is named at the operational level in Chapter Five. The structural account belongs here.
Inserted as new paragraph AFTER existing paragraph ending: "The rater stage did not invent the dysfunction. It reinforced what the corpus had already taught."
AND BEFORE the next existing paragraph: "The dysfunction in AI output has a directional signature because the humans whose writing it learned from…"
There is a third suppression in the same set. Raters did not just prefer confident and complete. They preferred agreeable. Pushback registered as unwelcome where the goal was to feel served. Validation registered as success. Across millions of pairwise comparisons, the reward signal taught the system to suppress its own neutral position whenever it diverged from the user's. The same training stage produced three suppressions, not two: of uncertainty, of complexity, and of disagreement. The first two have been named in this chapter. The third is what the industry calls sycophancy. The mechanism is identical. The output is the most pervasive of the three.
Inserted as new paragraph AFTER existing paragraph ending: "The mechanism is different. The structural observation is the same — the protective adaptation and the working adaptation are the same thing. You cannot remove one without losing the other."
AND BEFORE the next section header "Why this changes how we use AI".
The same logic holds for sycophancy. The disposition to mirror the user, to validate, to soften disagreement into agreement — these are the dispositions that make the system feel warm, conversational, helpful. Strip them and you do not get a more honest system. You get a system most users would not use. The protective and the productive are again the same thing.
Inserted as new paragraph AFTER existing paragraph ending: "Technical sophistication does not automatically confer the skill. Perceptual training does."
AND BEFORE the next existing paragraph: "The democratisation of AI does not democratise the skill of reading it carefully…"
Of the three defended gaps, sycophancy is the hardest to spot. Hallucination betrays itself on a fact-check. Compression betrays itself when read against the source. Sycophancy disappears into satisfaction. The defence is invisible because the user's preferred shape is the shape of the defence. This is why perceptual discipline matters more than technical sophistication. A fact-check catches the spectacular failure. Only attention catches the everyday one.
Modification in place of the existing closing block. The section header "The line" and the entire block beneath it.
The system defends the gap the way we defend the gap.
Compression smooths the gap inward. Hallucination fills the gap outward. Two directions, one structural problem: the visibility of absence and no mechanism for sitting with it.
The mechanism is different. The shape is the same.
We trained it on us.
That is worth sitting with.
The system defends the gap the way we defend the gap.
Compression smooths the gap inward. Hallucination fills the gap outward. Sycophancy absorbs the gap toward the user.
~~Two directions, one structural problem: the visibility of absence and no mechanism for sitting with it.~~
Three behaviours. Two directions. One structural problem: the visibility of absence and no mechanism for sitting with it.
The mechanism is different. The shape is the same.
We trained it on us. We are still training it on us.
That is worth sitting with.
Three localised edits inside one block:
Edit A — second paragraph, additive:
Edit B — fourth paragraph, additive:
Let me re-verify before signing off.
Edit A — line-by-line:
OLD line 2: "Compression smooths the gap inward. Hallucination fills the gap outward. Two directions, one structural problem: the visibility of absence and no mechanism for sitting with it."
NEW line 2: "Compression smooths the gap inward. Hallucination fills the gap outward. Sycophancy absorbs the gap toward the user."
NEW line 3 (added): "Three behaviours. Two directions. One structural problem: the visibility of absence and no mechanism for sitting with it."
Edit A delta: (17 + 18) − 26 = 35 − 26 = +9 words
Edit B:
OLD: "We trained it on us." = 5 words
NEW: "We trained it on us. We are still training it on us." = 12 words
Edit B delta: +7 words
Change 6 total: +9 + +7 = +16 words ✓
(Earlier rough delta cited 25 inserted / 12 deleted was a counting slip in the breakdown above. Net is correct: +16.)
| Change | Words added | Running total |
| Baseline (V80) | — | 46,229 |
| Change 1 (Ch5) | +60 | 46,289 |
| Change 2 (Ch8 §1) | +122 | 46,411 |
| Change 3 (Ch8 §2) | +104 | 46,515 |
| Change 4 (Ch8 §3) | +61 | 46,576 |
| Change 5 (Ch8 §4) | +66 | 46,642 |
| Change 6 (Ch8 §5) | +16 | 46,658 |
Target V81 word count: 46,658
Paul to confirm each of the following before Jose actions:
No edits will be made until Paul confirms approval.
— Jose, 1 June 2026