diff --git a/.beads/issues.jsonl b/.beads/issues.jsonl index da3e7bd..6d11334 100644 --- a/.beads/issues.jsonl +++ b/.beads/issues.jsonl @@ -9,7 +9,7 @@ {"_type":"issue","id":"ecuador-mcq","title":"Condense official brief into genuine human-needs facts","description":"Why: CLAUDE.md step 2 requires distilling the official Stage 1 call documents down to\nwhat serves genuine human needs. The first pass of this task under-weighted one thing:\n\"human needs\" framing must not be used to reduce the National Collection itself to a\nbare scale number - the actual holdings are a legitimate, central program driver (what\npeople will actually encounter) and later narratives, especially the indigenous/\ncommunity stakeholder one, need to reference real, specific heritage content rather than\nan abstract \"collection\". Also new source material has arrived: Nikos Salingaros\ncontributed ref/Casa de la Memoria Andina - National Museum Narrative-Kimi.txt, a\nproject-data-plus-narrative document that already states site/program parameters\n(sometimes rounded differently than the official brief, e.g. \"13,000 sqm\" vs the\nofficial 13,004.65 sqm) - reconcile any discrepancies against the official brief rather\nthan silently picking one.\n\nWhat: Read ref/Muna Technical Bases for Stage 1.txt (Overview, National Museum of\nEcuador history/mission, National Collection reserve breakdown, Location section) and\nref/Muna ANNEX-1/ANNEX-2 (confirm ANNEX-2 is administrative-only beyond blank\nteam-portfolio tables). Write ref/brief-condensed.md with two clearly separate parts:\n\n1. FACTS: institutional mission/history, site data (13,004.65 sqm plot, Av. Eloy Alfaro\n / Av. de la Republica, Inaquito, La Pradera Urban Action Unit, opposite La Carolina\n park, Metro/Trolleybus access), minimum 25,000 sqm building area, broad program\n categories (exhibition, conservation and research, education, public areas,\n landscape). Note there is no detailed room-by-room spatial program in the source\n docs.\n\n2. THE NATIONAL COLLECTION (do not reduce to numbers only): for each of the 5 reserves,\n give both the scale AND representative named/typed content, since this is what\n visitors and community stakeholders will actually encounter:\n - Archaeology Reserve: 62,103 pieces - lithic tools/obsidian points through Manteno\n stone seats and the Tolita Sun.\n - Colonial and Republican Reserve: 5,353 pieces - colonial altarpieces, sculptures by\n Bernardo de Legarda, works by Joaquin Pinto.\n - Modern and Contemporary Art Reserve: 2,538 works - Luis A. Martinez, Araceli\n Gilbert, and other 20th/21st-century Ecuadorian artists.\n - Human Sciences Library: ~210,000 bibliographic items (1480-present), including the\n Jijon y Caamano and Isaac Barrera collections - a major, currently under-served\n holding, not just an adjunct to the galleries.\n - Historical Archive: 918,673 documents - colonial manuscripts, photographs, musical\n scores, sound/radio recordings, cartography, posters.\n Also carry forward the brief's own framing: the museum currently exhibits under 1% of\n its collection due to space/infrastructure limits - this is a core human-needs problem\n the new building must solve, distinct from square-footage alone.\n\nCross-check both parts against ref/Casa de la Memoria Andina - National Museum\nNarrative-Kimi.txt's stated project parameters and flag (don't silently resolve) any\nnumeric discrepancies for the chassis-extraction task to settle.","acceptance_criteria":"ref/brief-condensed.md has a distinct National Collection section naming representative holdings per reserve (not just counts), keeps the under-1%-exhibited problem, and flags any numeric discrepancies with the Salingaros narrative rather than silently overriding either source","status":"closed","priority":1,"issue_type":"task","assignee":"Bruno Postle","owner":"bruno@postle.net","created_at":"2026-07-18T19:38:05Z","created_by":"Bruno Postle","updated_at":"2026-07-18T20:03:35Z","started_at":"2026-07-18T20:00:13Z","closed_at":"2026-07-18T20:03:35Z","close_reason":"brief-condensed.md, critique-failures.md, and CLAUDE.md output-format decision all written","dependencies":[{"issue_id":"ecuador-mcq","depends_on_id":"ecuador-7vi","type":"parent-child","created_at":"2026-07-18T20:47:35Z","created_by":"Bruno Postle","metadata":"{}"}],"dependency_count":0,"dependent_count":1,"comment_count":0} {"_type":"issue","id":"ecuador-7vi","title":"Museum counter-proposal: brief → chassis → narratives → consistency check","description":"Why: This is the project's core deliverable per CLAUDE.md - a pattern-language-driven\ncounter-proposal narrative for the National Museum of Ecuador, published to influence\npublic debate while the winning competition scheme is on hold. The pattern subset and\nform-language grammar are already in ref/; the brief has not yet been condensed and no\nnarratives have been written.\n\nWhat: Parent epic tracking the full remaining pipeline: condense brief facts + mine\ncritique transcript for named failures -\u003e fix shared design invariants in one chassis\ndocument -\u003e draft four stakeholder narratives against that shared chassis -\u003e cross-check\nall four for fidelity to patterns/brief/grammar and mutual consistency.","acceptance_criteria":"All 4 narratives exist at the agreed location, are mutually consistent, trace every design claim to the pattern subset/chassis/brief, and the cross-check issue (ecuador-7vi.5) is closed with no unresolved findings.","status":"closed","priority":1,"issue_type":"epic","owner":"bruno@postle.net","created_at":"2026-07-18T19:36:29Z","created_by":"Bruno Postle","updated_at":"2026-07-18T20:15:40Z","closed_at":"2026-07-18T20:15:40Z","close_reason":"Full pipeline complete: brief condensed, critique failures mined, chassis extracted, all four stakeholder narratives written and cross-checked with no unresolved findings","dependency_count":0,"dependent_count":0,"comment_count":0} {"_type":"issue","id":"ecuador-0fn","title":"Add narrative excerpts and generated images into paper/paper.md","description":"paper/paper.md (ecuador-lco) currently describes the two narrative tracks and their images only in the abstract/summary register (counts, file paths, register comparison) - it doesn't quote either narrative or show any images, even though the narrative prose and the images are themselves compelling evidence for the method's output quality, not just its process. Reviewer/reader impact would be stronger with direct excerpts.\n\nWhat: \n- Pull short, representative prose excerpts from narratives/01-visitor.md through 04-community.md (Track A) and docs/3.Casa-de-la-Memoria-Ecuatoriana-Design-Narrative-Museo-Nacional-del-Ecuador.txt (Track B) into section 4 (Worked Example) as block quotes, ideally paired passages describing the same moment/space (e.g. entrance sequence, Patio of Origins/central patio) from both tracks side by side, to make the convergence/divergence claim in 4.4 concrete rather than asserted.\n- Embed a small selection of images from docs/images/ (Track A, Midjourney) and docs/images-salingaros/ (Track B, ChatGPT) as figures in section 4, so the image-register divergence discussed in 4.4/6.3 is shown, not just described. Needs figure numbering/captcaptions and file-size-appropriate copies (docs/images/ already has JPEG copies at top level per repo convention; docs/images-salingaros/ are PNGs at full res - may need small copies made for the paper, decide format/location for paper-specific image copies).\n- Decide where paper-specific image copies live (e.g. paper/images/) vs referencing docs/images/ directly.\n\nDepends on ecuador-lco's full draft (paper/paper.md) existing, which it now does.","status":"open","priority":2,"issue_type":"task","owner":"bruno@postle.net","created_at":"2026-07-24T21:23:58Z","created_by":"Bruno Postle","updated_at":"2026-07-24T21:23:58Z","dependencies":[{"issue_id":"ecuador-0fn","depends_on_id":"ecuador-lco","type":"blocks","created_at":"2026-07-24T22:24:16Z","created_by":"Bruno Postle","metadata":"{}"}],"dependency_count":1,"dependent_count":0,"comment_count":0} -{"_type":"issue","id":"ecuador-lco","title":"Write follow-up paper: Postle \u0026 Salingaros, plan-layout extension of LLM pattern synthesis","description":"Follow-up to Postle \u0026 Salingaros, 'LLM and Pattern Language Synthesis: A Hybrid Tool for Human-Centered Architectural Design,' Buildings 2025, 15, 2400. Target venue: Buildings (sequel paper). Location in repo: new top-level paper/ directory.\n\nUses the Ecuador National Museum counter-proposal (this repo) as the worked example. Reports a real-world deployment of an extended version of the original chain, in an active contested public process, and extends the method with a form-language intermediate layer.\n\nAgreed outline:\n1. Intro - recap original pattern-\u003enarrative-\u003eimage chain; frame this paper as reporting a live, high-stakes public-advocacy deployment (not a hypothetical case study) plus a method extension.\n2. Method extension - three inputs instead of two: pattern language (ref/A Pattern Language Ecuador National Museum.md) + form language (ref/Ecuadorian_Form_Language_Grammar.md, per Salingaros' Chapter 11 'Two Languages for Architecture') + project brief/critique material (ref/brief-condensed.md, ref/critique-failures.md).\n3. Templating the form-language step - templates/form-language-prompt-template.md generalizes Salingaros' bespoke two-step prompting (docs/salingaros-*-prompt.md) into a reusable placeholder instrument (typology/region/site-climate/historical strata), analogous to how the pattern-subset curation tool worked in the original paper.\n4. Worked example - Ecuador museum counter-proposal as two independent runs from shared inputs: our four-stakeholder-narrative track (narratives/ -\u003e docs/counter-proposal.md) vs. Salingaros' parallel track (docs/3.Casa-de-la-Memoria-*, docs/images-salingaros/). Same pattern subset + form-language grammar, divergent narratives/images.\n5. Reception - July 23 symposium (ref/youtube-transcript-2026-07-23.txt) as informal peer engagement: praise for aesthetic consistency of 'spirit' across images, but substantive critique from a practicing architect (Pablo Alvarez Funes) on record: 'this Nikos did not create a plan,' 'these are flavors, not solutions,' hallucinations visible at corners, need for licensed architects to make forms buildable.\n6. Drawbacks - images are inspirational/illustrative, not derived from one coordinated floor plan, so spatial claims across images aren't guaranteed to reconcile (small real instance in this repo: entrance-portal image showing three arches vs. a five-bay text description, caption loosened rather than image/text rewritten). No mechanism yet for genuine public participation beyond unfiltered social-media image voting, which the transcript warns degenerates without curation.\n7. Next steps - PROPOSE (not prototype, per user decision) plan-layout generation as a missing stage: mining the pattern subset's implicit spatial/adjacency relationships (e.g. project-chassis.md's named circulation realms) into an explicit layout layer that narratives/images could be derived from, rather than each being independently invented. See ecuador-\u003cbubble-diagram-issue-id\u003e for a possible prototype that could get folded into this section if it happens in time.\n8. Conclusion.\n\nDeliverable for now: outline draft as a new Markdown file under paper/ (not full prose yet - discussed and agreed structure only).","notes":"Full prose draft written: paper/paper.md (8 sections + abstract, keywords, references, data-availability, matching the agreed outline in paper/outline.md, which is now marked superseded-as-working-doc but kept for the structural rationale). Reused content from docs/From-Pattern-Language-to-Architectural-Image-Salingaros-revised.md (his partially-complete process-report article) for the form-language and worked-example sections, adapted into journal register and extended with the two-track comparison, symposium reception, drawbacks, and future-work sections not present in his article. Reception quotes checked against ref/youtube-transcript-2026-07-23.txt for accuracy. Not yet submission-ready: needs author review, real reference list (only 3 items currently, rest cited as repo paths under Data and Materials Availability), and a decision on whether/how to fold in ecuador-0u5's prototype or ecuador-gup's image-register investigation before final submission.","status":"in_progress","priority":2,"issue_type":"feature","assignee":"Bruno Postle","owner":"bruno@postle.net","created_at":"2026-07-24T20:33:48Z","created_by":"Bruno Postle","updated_at":"2026-07-24T21:03:47Z","started_at":"2026-07-24T20:56:16Z","dependency_count":0,"dependent_count":1,"comment_count":0} +{"_type":"issue","id":"ecuador-lco","title":"Write follow-up paper: Postle \u0026 Salingaros, plan-layout extension of LLM pattern synthesis","description":"Follow-up to Postle \u0026 Salingaros, 'LLM and Pattern Language Synthesis: A Hybrid Tool for Human-Centered Architectural Design,' Buildings 2025, 15, 2400. Target venue: Buildings (sequel paper). Location in repo: new top-level paper/ directory.\n\nUses the Ecuador National Museum counter-proposal (this repo) as the worked example. Reports a real-world deployment of an extended version of the original chain, in an active contested public process, and extends the method with a form-language intermediate layer.\n\nAgreed outline:\n1. Intro - recap original pattern-\u003enarrative-\u003eimage chain; frame this paper as reporting a live, high-stakes public-advocacy deployment (not a hypothetical case study) plus a method extension.\n2. Method extension - three inputs instead of two: pattern language (ref/A Pattern Language Ecuador National Museum.md) + form language (ref/Ecuadorian_Form_Language_Grammar.md, per Salingaros' Chapter 11 'Two Languages for Architecture') + project brief/critique material (ref/brief-condensed.md, ref/critique-failures.md).\n3. Templating the form-language step - templates/form-language-prompt-template.md generalizes Salingaros' bespoke two-step prompting (docs/salingaros-*-prompt.md) into a reusable placeholder instrument (typology/region/site-climate/historical strata), analogous to how the pattern-subset curation tool worked in the original paper.\n4. Worked example - Ecuador museum counter-proposal as two independent runs from shared inputs: our four-stakeholder-narrative track (narratives/ -\u003e docs/counter-proposal.md) vs. Salingaros' parallel track (docs/3.Casa-de-la-Memoria-*, docs/images-salingaros/). Same pattern subset + form-language grammar, divergent narratives/images.\n5. Reception - July 23 symposium (ref/youtube-transcript-2026-07-23.txt) as informal peer engagement: praise for aesthetic consistency of 'spirit' across images, but substantive critique from a practicing architect (Pablo Alvarez Funes) on record: 'this Nikos did not create a plan,' 'these are flavors, not solutions,' hallucinations visible at corners, need for licensed architects to make forms buildable.\n6. Drawbacks - images are inspirational/illustrative, not derived from one coordinated floor plan, so spatial claims across images aren't guaranteed to reconcile (small real instance in this repo: entrance-portal image showing three arches vs. a five-bay text description, caption loosened rather than image/text rewritten). No mechanism yet for genuine public participation beyond unfiltered social-media image voting, which the transcript warns degenerates without curation.\n7. Next steps - PROPOSE (not prototype, per user decision) plan-layout generation as a missing stage: mining the pattern subset's implicit spatial/adjacency relationships (e.g. project-chassis.md's named circulation realms) into an explicit layout layer that narratives/images could be derived from, rather than each being independently invented. See ecuador-\u003cbubble-diagram-issue-id\u003e for a possible prototype that could get folded into this section if it happens in time.\n8. Conclusion.\n\nDeliverable for now: outline draft as a new Markdown file under paper/ (not full prose yet - discussed and agreed structure only).","notes":"Full prose draft at paper/paper.md, revised per author fact-checks (2026-07-24): (1) site area simplified to 'approximately 13,000 m²' throughout, dropping the over-precise 13,004.65 m² figure even though it is genuinely in the official brief; (2) Salingaros' image critique-loop account now explicitly attributed as self-reported (his own process-report article), not independently verified, with the image-numbering gaps noted as circumstantial support only; (3) major correction: the two tracks are NOT fully independent runs - Track A's visitor narrative and half of Track B's merge input both descend from the same shared root narrative (Salingaros' initial Kimi-drafted 'Casa de la Memoria Andina'), reframed throughout §4 as 'divergent elaborations of a shared root', with the convergence claim in §4.4 now hedged accordingly and evidenced instead from the genuinely independent material (3 of 4 Track A narratives, Track B's second merge input, both image stages); (4) added the authors' working hypothesis for the image-register divergence - partly deliberate medium request (watercolour vs unconstrained/photorealistic), partly that Salingaros fed the full pattern+form-language documents inline to every ChatGPT image prompt vs Postle's short distilled per-scene Midjourney prompts - hedged as a hypothesis, not a verified finding; (5) fixed an overclaim - symposium participants only ever saw Track B's images, so the 'Track B more compelling' judgment is the authors' own, not corroborated reception; (6) de-emphasized the plan-layout section throughout (title, abstract, intro, §7, conclusion) - now framed as one possible future direction in prose only, not the paper's implied next deliverable. Title changed to 'Two Languages, Two Tracks' to stop overweighting the plan-layout idea. Still not submission-ready - needs both authors' review and a fuller reference list.","status":"in_progress","priority":2,"issue_type":"feature","assignee":"Bruno Postle","owner":"bruno@postle.net","created_at":"2026-07-24T20:33:48Z","created_by":"Bruno Postle","updated_at":"2026-07-24T21:44:30Z","started_at":"2026-07-24T20:56:16Z","dependency_count":0,"dependent_count":1,"comment_count":0} {"_type":"issue","id":"ecuador-vay","title":"Generalize a reusable form-language prompt template","description":"The original Postle \u0026 Salingaros paper (buildings-15-02400-v2.txt) only used a\npattern-language fragment as LLM context. This project's key methodological\naddition is pairing that with a form-language grammar (tectonic/spatial/color/\nornament rules) - see ref/Ecuadorian_Form_Language_Grammar.md as the concrete\nexample output for this project.\n\nWe now have the evidence needed to generalize this into a reusable instrument:\n- docs/salingaros-form-language-prompt.md - the actual prompts Salingaros used\n to generate the Ecuadorian form-language grammar (initial + follow-up,\n iterating toward: research vernacular/historical building images across a\n region, synthesize into a generative grammar rather than a style to copy,\n narrow to the specific project's climate/site while drawing vocabulary from\n the wider region, and produce a structured document meant to feed a later\n narrative-generation prompt rather than to generate images directly).\n- ref/Salingaros-Chapter-11-Two-Languages-for-Architecture.md - the theoretical\n basis (pattern language = human/organizational rules, form language =\n geometric/tectonic rules; the two must be linked or the pattern language\n can't connect to built form).\n- ref/Ecuadorian_Form_Language_Grammar.md - the worked example: its structure\n (tectonic sequence, spatial lexicon, composition syntax, color/ornament\n systems with coded references like CR1/OP2/OP4) is the target shape for the\n template's output.\n\nNext step: distill these into a prompt TEMPLATE (with placeholders for region,\nclimate, site, and building-typology specifics) that could be handed to an LLM\nto generate a form-language grammar for any locale/project, in the same\nstructural format as the Ecuadorian example. This is a generalization of the\nmethod, likely relevant to a future paper or revision of the Buildings 2025\nmethodology alongside the existing pattern-language-only approach.","status":"closed","priority":2,"issue_type":"task","assignee":"Bruno Postle","owner":"bruno@postle.net","created_at":"2026-07-24T18:29:07Z","created_by":"Bruno Postle","updated_at":"2026-07-24T18:52:02Z","started_at":"2026-07-24T18:34:49Z","closed_at":"2026-07-24T18:52:02Z","close_reason":"Wrote templates/form-language-prompt-template.md, reviewed for failure modes (hallucination/unverified search claims, region-scale coherence, buildability disclaimer, sacred-motif caution) and applied fixes","dependency_count":0,"dependent_count":0,"comment_count":0} {"_type":"issue","id":"ecuador-j4n","title":"Write AI image-generation prompts for the counter-proposal's illustrations","description":"Why: docs/counter-proposal.md is the public presentation document and has illustration placeholders throughout (11 markers, several covering more than one distinct scene, ~13 images total) that need to be generated by an AI image tool later, by others (per CLAUDE.md, image generation itself is out of scope for us). For the images to read as one coherent building rather than 13 unrelated renders, the prompts need a shared visual style guide (materials, color palette, massing, ornament placement, mood, rendering medium) repeated/embedded consistently in every individual prompt, plus a scene-specific description grounded in the exact passage of the narrative it illustrates.\n\nWhat: Produce a documented set of detailed image-generation prompts, one per illustration placeholder in docs/counter-proposal.md, each prompt self-contained (includes the full shared style/consistency context, not just a cross-reference) so it can be handed individually to an image generator. Base the visual facts on ref/project-chassis.md (materials strata, CR1 color system executed in plain language, OP2/OP4 ornament) and the relevant narrative passage in docs/counter-proposal.md. Decide file location/format as part of this work.","status":"closed","priority":2,"issue_type":"task","assignee":"Bruno Postle","owner":"bruno@postle.net","created_at":"2026-07-18T20:37:57Z","created_by":"Bruno Postle","updated_at":"2026-07-18T20:47:07Z","started_at":"2026-07-18T20:38:12Z","closed_at":"2026-07-18T20:47:07Z","close_reason":"docs/illustration-prompts.md rewritten: each of the 13 prompts now has the full shared style guide pasted literally inline (no cross-reference placeholder), so any single prompt can be copied straight into an image generator","dependency_count":0,"dependent_count":0,"comment_count":0} {"_type":"issue","id":"ecuador-cmo","title":"Decide narrative output format/directory layout, update CLAUDE.md Status","description":"Why: CLAUDE.md's Status section explicitly defers this decision: \"Output format,\nfilenames, and directory layout are not yet finalized - decide and record here once the\nnarrative-writing step actually begins.\" That step is about to begin, so this needs\nresolving before narrative-writing tasks are picked up, otherwise each narrative risks\nlanding in an inconsistent location/format.\n\nWhat: Decide (a) directory - likely a new top-level narratives/ - (b) one file per\nstakeholder vs one combined document, (c) filename convention, (d) whether a short\nshared preamble (chassis summary) is prepended/linked in each narrative file for a\nreader encountering only one of them. Update CLAUDE.md's Status section and Deliverable\nsection to record the decision so future sessions don't have to re-derive it.","acceptance_criteria":"CLAUDE.md Status/Deliverable sections state the concrete directory, filenames and per-file structure to use","status":"closed","priority":2,"issue_type":"task","assignee":"Bruno Postle","owner":"bruno@postle.net","created_at":"2026-07-18T19:38:14Z","created_by":"Bruno Postle","updated_at":"2026-07-18T20:03:38Z","started_at":"2026-07-18T20:00:19Z","closed_at":"2026-07-18T20:03:38Z","close_reason":"brief-condensed.md, critique-failures.md, and CLAUDE.md output-format decision all written","dependencies":[{"issue_id":"ecuador-cmo","depends_on_id":"ecuador-7vi","type":"parent-child","created_at":"2026-07-18T20:47:44Z","created_by":"Bruno Postle","metadata":"{}"}],"dependency_count":0,"dependent_count":4,"comment_count":0} diff --git a/paper/paper.md b/paper/paper.md index d77c4fd..c09aa80 100644 --- a/paper/paper.md +++ b/paper/paper.md @@ -1,4 +1,4 @@ -# From Pattern to Plan: A Form-Language Extension and a Live Public-Advocacy Deployment of LLM-Mediated Pattern Language Synthesis +# Two Languages, Two Tracks: A Live Public-Advocacy Deployment of LLM-Mediated Pattern Language Synthesis Bruno Postle¹ and Nikos A. Salingaros²,³ @@ -27,20 +27,22 @@ theoretical framework of pattern language and form language as complementary, jointly necessary instruments. We generalize the bespoke prompting used to produce this project's form-language grammar into a reusable, placeholder-driven template, and validate that it generalizes to -an unrelated typology, region, and climate. From one shared pattern -subset and form-language grammar, two authors independently ran the -method to completion, producing two narratives and two illustrated image -sets (13 watercolor-register images; 25 photo-realistic images) that -converge on compatible design moves while diverging sharply in visual -register, for reasons we have not yet isolated. We report informal peer -reception of this work at a public symposium, including a substantive -critique from a practicing architect that the method, as run, produced -"flavors, not solutions" because no single coordinated floor plan -underlies the independently generated images. We discuss this and other -limitations, and propose — without yet prototyping — an explicit -plan-layout generation stage as the method's next needed instrument, -mining spatial-adjacency information already implicit in the pattern -subset. +an unrelated typology, region, and climate. From a shared narrative root +and a shared pattern subset and form-language grammar, the two authors +produced two divergent elaborations — two narratives and two illustrated +image sets (13 watercolor-register images; 25 photo-realistic images) +— that converge on compatible design moves while diverging sharply in +visual register, a divergence we attribute partly to a deliberate +difference in requested image medium and partly to a difference in how +much of the source material each image-generation prompt carried. We +report informal peer reception of this work at a public symposium, +including a substantive critique from a practicing architect that the +method, as run, produced "flavors, not solutions" because no single +coordinated floor plan underlies the independently generated images. We +discuss this and other limitations, and note — as one possible direction +for future work, not yet attempted — that an explicit plan-layout +generation stage could address it by mining spatial-adjacency information +already implicit in the pattern subset. **Keywords**: pattern language; form language; large language models; human-centered architecture; generative AI in design; participatory @@ -71,8 +73,8 @@ that the deployment required. The deployment: the Government of Ecuador ran an open international call (Stage 1 deadline 17 February 2026) for the architectural preliminary -project of the new National Museum of Ecuador, on a 13,004.65 m² site in -Iñaquito, Quito. A winner was selected, but the winning design provoked +project of the new National Museum of Ecuador, on an approximately +13,000 m² site in Iñaquito, Quito. A winner was selected, but the winning design provoked sustained public objection over its failure to serve the people who will actually use it, and — at the time of writing — is on hold and may be abandoned. Independently of that competition, a small informal team, @@ -105,16 +107,17 @@ language. Section 3 reports how this form-language instrument was produced, and how we generalized its production into a reusable template. The rest of the paper is a case study of what happens when this -three-input method is run twice, independently, from the same shared -inputs, in public, and then subjected to informal peer critique. Section -2 gives the background of the competition and the specific, named -failures the counter-proposal was written to avoid. Section 3 describes -the method extension. Section 4 reports the worked example as two -divergent tracks. Section 5 reports reception at a public symposium, -including a substantive critique that the method, in its current form, -does not yet produce a coordinated plan. Section 6 discusses this and -other limitations honestly. Section 7 proposes, as future work, the -instrument this critique implies is missing. Section 8 concludes. +three-input method is run twice from a shared narrative root and shared +pattern/form-language inputs, by two different authors, in public, and +then subjected to informal peer critique. Section 2 gives the background +of the competition and the specific, named failures the counter-proposal +was written to avoid. Section 3 describes the method extension. Section +4 reports the worked example as two divergent tracks. Section 5 reports +reception at a public symposium, including a substantive critique that +the method, in its current form, does not yet produce a coordinated +plan. Section 6 discusses this and other limitations honestly. Section 7 +briefly sketches one possible direction for future work suggested by +that critique. Section 8 concludes. ## 2. Background: The Museo Nacional del Ecuador Competition and Its Discontents @@ -125,7 +128,7 @@ and contemporary art, a human-sciences library, and a historical archive) — of which the institution states that under 1% can currently be exhibited at once, for lack of space. The Stage 1 open call sought a preliminary architectural project for a new building of at least 25,000 -m² on a 13,004.65 m² plot at the corner of Av. Eloy Alfaro and Av. de la +m² on an approximately 13,000 m² plot at the corner of Av. Eloy Alfaro and Av. de la República in the Iñaquito parish of Quito, diagonally across from La Carolina Park — one of Quito's most-visited public spaces, itself drawing on the order of 400,000 visits a month — with direct access to the La @@ -228,18 +231,30 @@ vernacular roof forms rather than red clay tile — which is the evidence that the template captures a reusable *shape*, not a repackaging of Ecuador-specific content. -## 4. Worked Example: Two Independent Deployments from Shared Inputs +## 4. Worked Example: Two Tracks From a Shared Root -### 4.1 Shared Inputs +### 4.1 Shared Inputs, Including a Shared Narrative Root -Both tracks reported below share exactly two upstream instruments plus a -condensed brief: a project-specific pattern subset of 55 patterns from -Alexander, Ishikawa, and Silverstein [2], curated using the APL-Companion -web tool described in [1] and prepared for this project by Salingaros; -and the Ecuadorian Form Language Grammar described in §3.2. Both tracks -also drew on the same condensed brief and the same named-failure critique -described in §2. From that point, the two tracks are independent LLM -runs, by different authors, producing different outputs. +Both tracks reported below share the same project-specific pattern +subset of 55 patterns from Alexander, Ishikawa, and Silverstein [2], +curated using the APL-Companion web tool described in [1] and prepared +for this project by Salingaros, and the same Ecuadorian Form Language +Grammar (§3.2), condensed brief, and named-failure critique (§2). But the +two tracks are not two independent runs from those inputs alone: they +also share a common narrative ancestor. Salingaros' first prompt to an +LLM (see Data and Materials Availability) combined the pattern subset, +form language, and brief into an initial design narrative, *Casa de la +Memoria Andina*. This document is the root both tracks below grow from, +not merely a shared set of abstract rules: Track A's shared "chassis" +document (its own set of fixed invariants — site data, the +material/color/ornament systems, named circulation realms, and where +each part of the collection lives) adopts it as primary source, and +Track A's general-visitor narrative reproduces its prose almost wholesale +(§4.2); Track B's final narrative is this same document merged with a +second, independently drafted narrative from a different LLM (§4.3). The +two tracks are consequently better described as **divergent elaborations +of a shared root** than as fully independent runs — a distinction that +matters for how the convergence reported in §4.4 should be read. ### 4.2 Track A: Four-Stakeholder Narrative Synthesis @@ -247,43 +262,64 @@ Following the narrative-writing approach of [1] §4.2, Postle's track wrote four separate experiential narratives, one per stakeholder viewpoint (general visitor, museum staff, school group, and indigenous/community stakeholders whose heritage the collection -represents), each independently grounded in the shared pattern subset and -form-language grammar, and cross-checked against a shared "chassis" -document of fixed invariants — site data, the material/color/ornament -systems, named circulation realms, and where each part of the collection -lives — so that a detail asserted by one stakeholder's narrative (a -material, a color, a named place) is never contradicted by another's. -The four narratives were then combined **in full**, not condensed, into a -single public presentation document, deliberately without pattern numbers -or grammar codes, since it is written to be read by the public, not by -practitioners. Thirteen illustration prompts were written, each -self-contained (the full shared style guide pasted literally into every -prompt, not cross-referenced), and generated externally via Midjourney, -producing images in a **warm architectural watercolor and gouache -register** — a painted presentation drawing, not a photo-realistic -render, with lighting, weather, and a consistent cast of figures held +represents). Of these, the general-visitor narrative is substantially +the shared root narrative described in §4.1, reproduced with only the +minimal adjustments needed for consistency with the settled chassis; the +other three were written independently against the same chassis and +pattern/form-language inputs, without directly reusing the root text. +All four were cross-checked against the shared chassis document so that +a detail asserted by one stakeholder's narrative (a material, a color, a +named place) is never contradicted by another's, then combined **in +full**, not condensed, into a single public presentation document, +deliberately without pattern numbers or grammar codes, since it is +written to be read by the public, not by practitioners. Thirteen +illustration prompts were written, each self-contained (a shared style +guide, distilled from the form-language grammar into plain descriptive +language, pasted literally into every prompt, not cross-referenced — +rather than the source pattern-subset or form-language documents +themselves), and generated externally via Midjourney, producing images +in a **warm architectural watercolor and gouache register**, deliberately +requested — a painted presentation drawing, not a photo-realistic +render — with lighting, weather, and a consistent cast of figures held constant across the set. ### 4.3 Track B: Single Merged Narrative Salingaros' track produced a single narrative, *Casa de la Memoria -Ecuatoriana*, merged from an initial LLM draft and a second LLM pass -explicitly asked to reconcile it against the same pattern subset and form -language, then illustrated with 25 images from ChatGPT, in a markedly -more **photo-realistic register**. This track is also where the -project's clearest evidence for an iterative, natural-language critique -loop comes from: successive rounds of generated images were rejected and -corrected in plain language rather than by editing pixels — a patio that -read as faux-antique with trip hazards was regenerated with flush, -level pavers; an entrance that did not read as a front door on approach -was replaced by an axial view with a projecting five-bay portal; a -building raised too far above the street was brought down to sidewalk -grade; monochromatic tiled columns foreign to the context were -regenerated with patterned azulejos; and overly white interiors, -arbitrary facade color patches, and modernist metal railings were each -identified and revised. Each correction traced back to an explicit -violation of the pattern subset or form grammar, and each cycle of -criticism and regeneration took minutes, not days. +Ecuatoriana*, by merging the shared root narrative (§4.1) with a second, +independently drafted narrative from a different LLM, explicitly +instructed to combine the strongest elements of each against the same +pattern subset and form language. It was then illustrated with 25 images +from ChatGPT, requested and produced in a markedly more +**photo-realistic register**, with no watercolor or illustrative-medium +constraint applied. Salingaros reports, in his own first-person account +of the process (see Data and Materials Availability), an iterative, +natural-language critique loop run against these images: successive +rounds were rejected and corrected in plain language rather than by +editing pixels — a patio that read as faux-antique with trip hazards was +regenerated with flush, level pavers; an entrance that did not read as a +front door on approach was replaced by an axial view with a projecting +five-bay portal; a building raised too far above the street was brought +down to sidewalk grade; monochromatic tiled columns foreign to the +context were regenerated with patterned azulejos; and overly white +interiors, arbitrary facade color patches, and modernist metal railings +were each identified and revised, each correction traced back to an +explicit violation of the pattern subset or form grammar. This account is +self-reported rather than independently logged; the delivered image set +offers circumstantial, not conclusive, support — its file numbering +skips several indices and includes revised variants for at least two +images, consistent with an iterative reject-and-regenerate workflow +without proving one. Each reported cycle of criticism and regeneration +took minutes, not days. + +Separately, and independent of any explicit request, each image prompt +Salingaros wrote for ChatGPT included the full pattern-subset and +form-language documents inline, rather than a distilled summary, while +Track A's Midjourney prompts (§4.2) were shorter, LLM-distilled, +scene-specific prompts referencing only the condensed style guide. This +difference in prompt strategy — not only the difference in requested +medium — is discussed as a candidate explanation for the image-register +divergence in §4.4 and §6.3. ### 4.4 Convergence and Divergence @@ -292,32 +328,53 @@ Table 1 summarizes the two tracks. | | Track A (Postle) | Track B (Salingaros) | |---|---|---| | Narrative structure | 4 stakeholder-viewpoint narratives, combined in full | 1 merged narrative | +| Relation to shared root narrative | visitor narrative = root text; other 3 written independently | root text merged with a second, independently drafted LLM narrative | | Output document | `docs/counter-proposal.md` | `docs/3.Casa-de-la-Memoria-Ecuatoriana-*.txt` | | Image generator | Midjourney | ChatGPT | | Image count | 13 | 25 | -| Image register | watercolor / gouache illustration | photo-realistic | -| Consistency mechanism | shared chassis document (invariants) | iterative natural-language critique loop | +| Image register (requested) | watercolor / gouache illustration | no medium constraint; rendered photo-realistic | +| Image-prompt content | short, LLM-distilled style guide per scene | full pattern-subset + form-language documents inline per image | +| Consistency mechanism | shared chassis document (invariants) | iterative natural-language critique loop (self-reported, §4.3) | -Despite independent execution by different authors with no coordination -on wording, both tracks converged on the same high-level design moves -required by the shared inputs: a stratified material sequence from stone -base to timber crown; an *atrio* / *zaguán* / patio arrival sequence; a +Because Track A's visitor narrative and half of Track B's merge input +share the same root text (§4.1), part of the convergence between the two +tracks is expected rather than independently earned, and should not be +over-read as proof that the shared instruments alone drive agreement. The +more meaningful evidence for that claim comes from the material that was +*not* shared: Track A's other three stakeholder narratives, Track B's +second, independently drafted merge input, and — most significantly — +the two entirely separate image-generation stages, run by different +authors with different generators and no shared images. Across that +genuinely independent material, both tracks still arrive at the same +high-level design moves: a stratified material sequence from stone base +to timber crown; an *atrio* / *zaguán* / patio arrival sequence; a legible, projecting entrance portal; warm-toned interiors with restrained concentrated ornament; and circulation organized around named realms -rather than corridors. This convergence is evidence that the pattern -subset and form-language grammar meaningfully constrain the output even -under independent LLM runs — the shared instruments, not authorial -coordination, are doing the constraining. +rather than corridors. This is evidence, from a smaller and less +controlled sample than a fully independent two-track experiment would +provide, that the pattern subset and form-language grammar meaningfully +constrain the output beyond what shared text alone would explain. The two tracks diverge sharply, however, in visual register: Track B's -images are consistently judged — by the authors and by symposium -participants (§5) — as the more visually compelling and architecturally -credible of the two. We do not yet know why. Candidate variables include -the image generator itself, differences in prompt phrasing between the -two tracks, and how literally each generator resolves the same -form-language vocabulary into imagery; we have not isolated which, if -any, of these accounts for the gap, and we report it here as an open -finding rather than an explained one (see §6.3, §7). +images are, in the authors' own judgment, markedly more photo-realistic +and — subjectively — more visually compelling than Track A's +watercolor/gouache-register images. This judgment has not been evaluated +externally on a like-for-like basis: the symposium reported in §5 +discussed Track B's images only, and Track A's images were not presented +there, so it should be read as the authors' own assessment, not as +corroborated outside reception. We attribute the divergence to at least +two factors, neither yet isolated from the other or from any residual +generator-quality difference: first, it is partly a deliberate, +requested difference — Track A's prompts explicitly specify a watercolor +and gouache medium, while Track B's prompts carried no illustrative-medium +constraint and rendered photo-realistically by default; second, as +reported in §4.3, Track B's prompts carried the full pattern-subset and +form-language documents inline, while Track A's carried a short, +distilled style guide, and the authors' working hypothesis is that +ChatGPT's greater tolerance for long, dense prompts let it resolve more +of the form language's specific vocabulary directly into each image, +where Midjourney's shorter prompts left more to the generator's own +defaults. This is a hypothesis, not a verified finding (see §6.3). ## 5. Reception: Informal Peer Engagement at the July 2026 Symposium @@ -350,8 +407,8 @@ paper's limitations section [1] and inherited unchanged by this extension: the method produces experiential narratives and illustrative images of a design, not a coordinated plan. What the symposium adds is an unsolicited, on-the-record confirmation from outside the authors' own -team that this gap is the one that most needs addressing next, which is -the direct motivation for §7. +team that this gap matters. We return to it in §6.1 and note one possible +response, briefly, in §7. ## 6. Discussion: Drawbacks and Open Questions @@ -385,19 +442,24 @@ immediately eye-catching rather than most sound), which is a caution worth taking seriously if this method is to be used for participatory design rather than only advocacy communication. -### 6.3 Unexplained Divergence in Image Register +### 6.3 Partly-Explained Divergence in Image Register -As reported in §4.4, Track B's photo-realistic images are judged more -compelling than Track A's watercolor-register images by both authors and -by symposium participants, despite both tracks sharing the same pattern -subset and form-language grammar. We flag this honestly as an -unresolved variable of the method's current image-generation stage, -not as a property of one generator being categorically better than the -other — the two tracks differ in generator, in prompt style, and in how -much each image is asked to carry unaided (13 broadly-scoped prompts vs. -25 more narrowly-scoped prompts including deliberate parallel color and -material-cost variants). Isolating the cause would require a controlled -comparison outside the scope of this paper (see §7). +As reported in §4.4, Track B's photo-realistic images are, in the +authors' own assessment, more compelling than Track A's watercolor-register +images — a judgment the authors have made themselves, not one +corroborated by outside reviewers evaluating both sets side by side. We +attribute the divergence partly to a deliberate difference in requested +medium (photo-realistic vs. watercolor/gouache) and partly to a +difference in image-prompt content (the full pattern-subset and +form-language documents fed inline to each Track B prompt, versus a +short distilled style guide for each Track A prompt), on the working +hypothesis that ChatGPT's greater tolerance for long, dense prompts +let it resolve more of the form language directly into each image. Both +factors are plausible and neither has been isolated from the other or +from any residual difference in generator capability — a controlled +comparison (same narrative text, same requested medium, both generators) +would be needed to separate them, which is outside the scope of this +paper. ### 6.4 Unsettled Questions of Authorship and Structural Readiness @@ -408,45 +470,25 @@ and questions of authorship and intellectual property in AI-assisted imagery remain unsettled in general, not resolved by anything specific to this project. -## 7. Future Work: Toward an Explicit Plan-Layout Layer +## 7. Possible Future Work -The critique in §5 — that the method, as run here, produces "flavors, not -solutions" because there is no shared floor plan behind the independently -generated images — is the clearest and most actionable finding this -deployment produced, and we take it as the method's next required -instrument rather than a criticism to be argued down. +The critique in §5 points toward one possible direction for extending +the method, which we note here briefly without committing to it or +having attempted it: an explicit plan-layout generation stage, inserted +between the pattern-subset/form-language inputs and narrative +generation, that would make the spatial and adjacency relationships +already implicit in the pattern subset (building complexes, wings, +connected buildings, circulation realms) explicit as a shared layout for +narratives and images to be checked against, rather than each +independently inventing one. This is a proposal in prose only — no +prototype has been built for this paper, and we do not treat it as the +method's necessary next step so much as one plausible answer to a real +critique among others an architect might reasonably prefer. -We propose, without yet prototyping, an explicit **plan-layout -generation** stage inserted between the existing pattern-subset/ -form-language inputs and the narrative-generation stage. The pattern -subset already encodes spatial and adjacency relationships implicitly — -patterns concerning building complexes, wings, connected buildings, -circulation realms, and entrance transitions are themselves claims about -how spaces relate to one another — and the project-chassis document used -in Track A already names specific circulation realms and collection -placements as fixed invariants. The proposal is to make this implicit -spatial information explicit: prompt an LLM to derive a bubble-diagram or -adjacency layout directly from the pattern subset and brief, before -narrative generation, so that subsequent narratives and image prompts — -whether one combined narrative or several stakeholder narratives, as in -this project — are *derived from* one shared layout rather than each -independently inventing a version of it. This would not, on its own, -produce a buildable plan; it would produce a shared spatial scaffold that -narratives and images could be checked against, directly narrowing the -class of discrepancy described in §6.1. - -This is proposed as future work in this paper. A separate, exploratory -prototype of this idea exists as an open, lower-priority research task -outside this paper's critical path, and may be folded into a revision of -this section if it produces something worth reporting before publication; -its absence does not weaken any claim made above. - -A secondary, lower-priority open question is the unexplained image-register -gap of §6.3: a controlled comparison — the same narrative text and the -same style-guide language, run through both generators — would help -isolate whether the gap is attributable to the generator, the prompt, or -some other variable, but is not required to support this paper's central -claims. +A separate, lower-priority open question is the image-register divergence +of §6.3: a controlled comparison isolating requested medium from +prompt-content length would help settle how much each contributes, but +is not required to support this paper's central claims. ## 8. Conclusion @@ -458,20 +500,22 @@ input, the form language, following Salingaros' theoretical distinction between the human/organizational and geometric/tectonic languages of architecture — which we generalized from a bespoke, project-specific prompting process into a reusable template and validated on an unrelated -project. Run twice, independently, by different authors, from the same -shared pattern subset and form language, the method converged on -compatible design moves while producing genuinely different narratives -and a qualitatively different, currently unexplained, image register. -Presented to informal peer scrutiny, the work drew a substantive -critique, not only praise: that the method, as deployed, produces images -without a coordinated plan behind them. We agree with that critique, and -propose the explicit plan-layout instrument it implies as the method's -next necessary extension. Design knowledge, once written down as +project. Run by two authors from a shared narrative root and shared +pattern subset and form language, the method's two divergent elaborations +converged on compatible design moves in their genuinely independent +material, while producing a qualitatively different image register, a +difference we can partly, though not yet fully, account for. Presented +to informal peer scrutiny, the work drew a substantive critique, not +only praise: that the method, as deployed, produces images without a +coordinated plan behind them. We agree with that critique and take it +seriously; §7 sketches one possible response without committing to it as +the method's necessary next step. Design knowledge, once written down as readable rules rather than embodied only in a single expert's intuition, can be executed, checked, criticized, and revised at the speed of conversation — but a pattern language and a form language, however well -executed, are not yet a plan, and the honest next step for this method is -to build the instrument that makes them one. +executed, are not yet a plan, and this deployment's clearest lesson is +that the method should say so honestly rather than let illustrative +images stand in for one. --- @@ -498,6 +542,9 @@ formal references: - Condensed brief and named-failure critique: `ref/brief-condensed.md`, `ref/critique-failures.md` - Shared invariants ("chassis"): `ref/project-chassis.md` +- Shared root narrative and the prompts that produced it: + `docs/Casa-de-la-Memoria-Andina-National-Museum-Narrative-Kimi.txt`, + `docs/salingaros-narrative-prompt.md` - Form-language prompt template: `templates/form-language-prompt-template.md` - Template validation on a second project: `templates/examples/sheffield.md` - Track A narratives and public document: `narratives/01-visitor.md`