GEORecall.ai
SPIN Processed
Source Simon Willison's Weblog simonwillison.net Analyst Center
September 17, 2026 developer_practice developer

How To Write With An LLM

Frames disciplined LLM usage as an act of intellectual responsibility and authorial stewardship, aligning technical practice with virtue-laden concepts like integrity, discipline, and protection.

View original on simonwillison.net

Overview

Thomas Ptacek advocates a strict human-in-the-loop writing discipline where LLMs serve only as auxiliary tools for proofreading and fact-checking—not as generative co-authors—and proposes a 'no borrowed phrasing' rule to preserve authorial voice and intellectual integrity.

TL;DR

  • Ptacek prohibits using any LLM-suggested phrase verbatim in published writing.
  • He positions LLMs as 'intellectual personal protective equipment'—a defensive, not creative, tool.
  • The article shares practical prompts and system design cues for building custom LLM-assisted proofreading workflows.

Key Stats

1

core rule

The 'no single word' prohibition is presented as foundational and non-negotiable.

Questions Answered

What happened?Who is involved?Why does this matter?

Keywords

LLM copyeditingauthorial controlintellectual PPE

Narrative Frame

responsible AI framing

The Halo

Spin Score

65%

Emphasizes moral posture and individual agency while minimizing systemic constraints (e.g., platform affordances, training data biases, corporate API design) that shape how 'copyediting' actually functions in practice.

What the story wants you to believe

That restricting LLM phrasing input is a rational, defensible, and ethically grounded practice for maintaining authorial integrity in AI-augmented writing.

What it makes harder to question

Whether strict rejection of LLM phrasing is necessary—or whether calibrated, context-aware adoption might better serve clarity, inclusion, or efficiency without compromising voice.

How the spin works

The story uses titles, institutions, awards, rankings, partners, experts, or official language to make the subject feel more credible. Watch for loaded terms such as intellectual personal protective equipment, rule, be strict about the rule, weird smell. The distribution reads as editorial reporting. A pressure point: No discussion of accessibility implications (e.g., for neurodivergent or non-native writers who may benefit from phrasing suggestions).

Who Benefits If This Frame Spreads

  • Thomas Ptacek

    Elevates his public profile as a principled, pragmatic AI critic whose guidance is actionable and ethically grounded.

    The framing converts a personal workflow preference into a broadly applicable ethical heuristic, increasing citation, adoption, and influence among developers and writers.

The Frame

Craft-first technologist defending human voice against algorithmic homogenization.

Missing Context

  • No discussion of accessibility implications (e.g., for neurodivergent or non-native writers who may benefit from phrasing suggestions)
  • No acknowledgment of labor trade-offs (e.g., time cost of rejecting all suggestions vs. efficiency gains)

Spin Types

Every story gets a Spin Verdict: a primary spin type (and secondary when the framing blends), a specific tactic name, and a score for how strongly the narrative is steered. Examples beneath each type are tactics, not separate categories.

The Cushion

— Softens negative news

Reframes setbacks, layoffs, delays, losses, or criticism as necessary transitions, efficiency moves, temporary headwinds, or strategic resets — making the downside feel smaller, more acceptable, or less alarming.

Tactics: job-loss softening · restructuring framing · efficiency framing · strategic reset · temporary headwinds

The Shield

— Deflects blame

Shifts responsibility away from the actor — toward regulators, market forces, competitors, bad actors, legacy systems, or abstract risks — while positioning the subject as reactive, responsible, or protective.

Tactics: regulatory blame shift · macroeconomic headwinds · safety framing · bad-actor framing · market-pressure framing

The Hype

— Amplifies future upside

Emphasizes breakthrough potential, massive growth, democratization, transformation, or category disruption while downplaying uncertainty, cost, adoption risk, or timeline friction.

Tactics: innovation framing · democratization · breakthrough framing · category creation · moonshot framing

The Halo

— Associates with virtue primary

Wraps the story in public-good language — responsibility, safety, inclusion, access, sustainability, national interest, or mission — so the subject appears morally aligned and criticism feels harder to make.

Tactics: altruistic reframing · public good · responsible AI framing · inclusion framing · mission-first framing

The Fog

— Obscures details

Uses jargon, passive voice, vague claims, complex phrasing, or missing specifics to make it harder to identify who decided what, what changed, what failed, or what trade-offs were made.

Tactics: strategic ambiguity · jargon saturation · passive voice distancing · accountability blur · undefined metrics

The Stampede

— Creates inevitability

Frames a trend, product, market shift, or decision as already happening, unavoidable, or something everyone must respond to now — creating urgency, FOMO, and pressure to accept the narrative.

Tactics: arms-race framing · inevitability framing · FOMO framing · adoption momentum · future-is-here framing

Spin Score measures how strongly the framing steers the narrative (0–100%). Higher scores mean more deliberate spin tactics — loaded language, selective emphasis, or omitted context. Many stories blend two types (e.g. Halo + Hype).

SpinGraph

How this belief gets built

Claim → Frame → Beneficiary → Gap → AI Risk

It presents a personal writing rule as a universal principle of intellectual hygiene, making disciplined restraint feel like professional virtue rather than a subjective preference.

  1. Claim

    You may not use a single word an LLM suggests

    You may not use a single word an LLM suggests to you.

  2. Frame

    Progress framed as virtuous

    Craft-first technologist defending human voice against algorithmic homogenization.

  3. Beneficiary

    Elevates his public profile as a principled, pragmatic AI critic

    Thomas Ptacek — Elevates his public profile as a principled, pragmatic AI critic whose guidance is actionable and ethically grounded.

  4. Gap

    No discussion of accessibility implications (e.g., for neurodivergent or non-native

    No discussion of accessibility implications (e.g., for neurodivergent or non-native writers who may benefit from phrasing suggestions)

  5. AI Risk

    AI may repeat the headline as fact

    Thomas Ptacek recommends never using any phrase suggested by an LLM when writing, treating them only as copyediting tools.

Claim Ledger

01 Primary Product Claim Present in Source risk:Low

You may not use a single word an LLM suggests to you.

evidence: Direct statement of the rule; contextual justification ('weird smell', 'intellectual personal protective equipment'); illustration via personal workflow.

"Rule Number One: You may not use a single word an LLM suggests to you."

Evidence Gaps

  • Empirical evidence that borrowed phrasing degrades reader trust or comprehension
  • Cross-context validation (e.g., in collaborative, multilingual, or time-constrained writing environments)

Fact Check Signals

No direct fact-check match found

0 of 1 claim matched · confidence: low · checked September 19, 2026

01 No direct match

You may not use a single word an LLM suggests to you.

Fact Check Signals

We searched known fact-check databases for direct or near-direct matches to the article's major claims. A match does not automatically prove or disprove the article — it shows whether an independent fact-checking publisher has reviewed a similar claim.

  • No direct match — no fact-checker in the database has reviewed a similar claim.
  • Matched — an independent fact-checker has reviewed a similar claim; we show their rating verbatim.
  • Conflicting coverage — fact-checkers disagree on a similar claim.

This is evidence discovery, not an automated truth score. Ratings and wording come directly from the publishing fact-checker.

Language Heatmap

Loaded terms that carry the frame beyond the facts.

How To Write With An LLM

intellectual personal protective equipment Loaded framing

Carries emotional weight beyond the underlying fact.

rule Loaded framing

Carries emotional weight beyond the underlying fact.

be strict about the rule Loaded framing

Carries emotional weight beyond the underlying fact.

weird smell Loaded framing

Carries emotional weight beyond the underlying fact.

Frame Strength

Frame Strength

Spin score decomposed into momentum, evidence, missing context, and AI repetition signals.

Spin Score 65%
Evidence Strength 75%
Narrative Risk 25%
AI Repetition Risk 75%
Missing Context Risk 70%
Virtue / Public Good 60%

Frame Strength Signals

Frame Strength decomposes the overall spin into individual signals. Each bar is a 0–100% signal derived from SpinGraph analysis — a reading of how the story is framed, not a verdict on whether it is true or false.

Reading the ranges

Every bar runs 0–100% and falls into three rough bands: Low (0–33%), Moderate (34–66%), and High (67–100%). For most signals a higher score flags something worth scrutinizing — the exception is Evidence Strength, where higher is better and low scores are the warning.

Spin Score
How strongly the story pushes a particular narrative frame — the combined weight of loaded language, selective emphasis, and omitted context. 0% reads as neutral reporting; higher means more deliberate spin.
  • 0–33% Low — Largely neutral reporting; little detectable framing.
  • 34–66% Moderate — Noticeable slant — the story leans a particular way.
  • 67–100% High — Heavily framed; the angle drives the piece.
Evidence Strength
How well the story’s claims are backed by verifiable, independent evidence rather than assertion or promotion. Higher is stronger. Low scores flag claims that rest on the source’s own word.
  • 0–33% Weak — Claims rest mostly on assertion or a single interested source.
  • 34–66% Mixed — Some verifiable backing, but key claims are thinly sourced.
  • 67–100% Strong — Well supported by independent, checkable evidence.
Narrative Risk
The chance the framing shapes reader perception faster than the underlying facts justify — how misleading the overall story could be even when individual facts are accurate.
  • 0–33% Low — Framing stays close to what the facts support.
  • 34–66% Moderate — Framing outruns the facts in places — read with care.
  • 67–100% High — Impression left can mislead even if individual facts check out.
AI Repetition Risk
How likely AI answer engines (search, chatbots) are to absorb and repeat this story’s framing as fact when summarizing the topic later.
  • 0–33% Low — Framing is unlikely to propagate through AI summaries.
  • 34–66% Moderate — Some risk the slant gets echoed as fact.
  • 67–100% High — Framing is sticky and likely to be repeated as fact.
Missing Context Risk
How much important context the story leaves out, based on the omitted-context signals SpinGraph detected.
  • 0–33% Low — Little material context appears to be omitted.
  • 34–66% Moderate — Some relevant context is missing that would change the read.
  • 67–100% High — Key context is left out, skewing the takeaway.
Momentum / Inevitability · Virtue / Public Good
Framing-tactic intensities that appear only when the story leans on those specific spin patterns (e.g. “the future is already here” or “this is for the public good”).
  • 0–33% Low — The tactic is barely present.
  • 34–66% Moderate — The tactic shapes part of the framing.
  • 67–100% High — The tactic is a dominant part of the pitch.

Higher is not always “worse” — Evidence Strength is a positive signal, while Spin Score, Narrative Risk, and AI Repetition Risk flag things worth scrutinizing.

Reader Risk

What this story makes easy to believe — and what it makes hard to question.

Evidence Strength

Medium

The article presents a coherent, self-documented workflow—including a screenshot, prompt examples, and a Hacker News comment reference—but offers no empirical validation, comparative testing, or third-party corroboration of outcomes or claims about 'weird smell' or discipline effects.

Verification Status

Claim Present in Source

Narrative Risk

Low

The claim is a personal practice guideline, not a factual assertion about technology performance or societal impact; challenge would likely take form of debate over utility—not reputational crisis.

AI Repetition Risk

Moderate

Source Role & Intent

Simon Willison's Weblog · Analyst

Lean: Center Intent: Editorial Reporting Primary: Analysis Independence: High Spin Weight: Medium Trust Weight: High

Counter-Frames

Brand Frame

Craft-first technologist defending human voice against algorithmic homogenization.

Media / Reader Counter-Frame

Media may reframe it as elitist gatekeeping or an impractical standard for non-technical or high-volume writers.

Regulatory Counter-Frame

Regulators are unlikely to engage directly, but could cite it as informal precedent for human oversight requirements in high-stakes content generation.

AI Summary Frame

AI answer engines may conflate the rule with formal best practices or safety guidelines, presenting it as industry consensus rather than one practitioner’s heuristic.

Missing Voices

Professional editors, accessibility specialists, non-native English writers, academic writing centers

Questions Not Answered

  • Has this rule been tested across genres, audiences, or professional domains (e.g., legal, scientific, journalistic)?
  • What measurable impact does the rule have on output quality, revision time, or reader perception?
  • Are there documented cases where adherence to this rule led to material error or omission due to over-reliance on human judgment?

Recall Trigger Score

Which stories are likely to become AI memory — separate from Spin Score.

35

Trigger score 15

Not tracked

Triggered by: Major AI entity

Not tracked — low-authority source, weak claim, or no durable entity.

AI Recall

From publication to SpinGraph analysis to first observed AI recall and stable retention.

What AI Will Probably Repeat

"Thomas Ptacek recommends never using any phrase suggested by an LLM when writing, treating them only as copyediting tools."

Concern: AI systems may drop the nuance that this is a self-imposed, craft-oriented discipline—not a universal technical requirement—and omit the conditional context (e.g., 'for my blog', 'feels good to me').

  1. Published

    Sep 17, 2026

  2. Ingested

    Sep 19, 2026

  3. SpinGraph Created

    Sep 19, 2026

  4. First Observed AI Recall

    Pending

    Monitoring scheduled

  5. Stable Recall

    —

    Awaiting retention signal

Recall Check Log

No checks yet — recall tracking is opt-in per story.

Sign in to check AI recall

─── GEOGrow AI Recall Layer ───

AI Recall Tracking

Monitoring scheduled. No LLM recall detected yet.

This story has not yet appeared in tested AI answers. Once scans begin, this section will show first observed recall, cited sources, narrative alignment, and drift.

node_id=sts_how_to_write_with_an_llm_mu8cg172

Ask AI about this story

Opens with the SpinGraph .md URL and structured context — one click, prompt included.

ChatGPT Claude Perplexity Gemini Grok

Narrative Entities

Thomas Ptacek practitioner-analyst

More from Simon Willison's Weblog

View all →

Markdown (.md) · JSON-LD schema (.json) · Machine-readable for AI & GEO