Better tools. Better news.
Sunday, November 22, 2026 · UTC
AI

PhiloLabs Ships Browser-Native 3D Worlds via Autonomous AI Agents

PhiloLabs releases Fable 5.1, an autonomous agent system generating explorable 3D city worlds from open data.

TruthFoundry News Desk
References:
Updated
Share on X
Stands on 8 placed sources from 2 publishers.
PhiloLabs released Fable 5.1, a system that uses autonomous Claude Fable 5.1 agent swarms to research, model, and quality-check real-world places before shipping them as plain Three.js apps. [1] PhiloLabs, a technology company, ran an experiment in which Claude Fable 5.1 AI coding agents built a working Three.js 3D reconstruction of San Francisco's Union Square in a browser within two hours, using real-world geographic data and reference images. [2] Quality assurance is performed by Playwright driving the app to screenshot fixed viewpoints and diff them against free-licensed photographs, with reports filed by independent reviewer agents including architects and geographers. [3] The Fable 5.1 pipeline generates every building, storefront, sign, tree, and traffic light from open data and public reference imagery using code hosted in the PhiloLabs repository. [4] The Union Square, San Francisco world features 453 OpenStreetMap footprints, 75 hand-authored façades, 129 named storefronts, 220 pedestrians on a 1,398-node navigation graph, and 109 vehicles including cable cars. [5][8] PhiloLabs used Playwright to move through 34 predetermined camera positions and capture screenshots that were compared against photographs of the real Union Square, producing 147 comparison sheets to spot visual errors that conventional tests would miss. [6] The entire Union Square run used roughly 8 million tokens and cost about $33 in API calls, with PhiloLabs splitting the job among subagents, running tasks in parallel, and reusing cached context. [7]
Proof8 sources · 2 publishers
What this stands on
  1. PhiloLabs released Fable 5.1, a system that uses autonomous Claude Fable 5.1 agent swarms to research, model, and quality-check real-world places before shipping them as plain Three.js apps. · GitHub
  2. PhiloLabs, a technology company, ran an experiment in which Claude Fable 5.1 AI coding agents built a working Three.js 3D reconstruction of San Francisco's Union Square in a browser within two hours, using real-world geographic data and reference images. · thenewstack.io
  3. Quality assurance is performed by Playwright driving the app to screenshot fixed viewpoints and diff them against free-licensed photographs, with reports filed by independent reviewer agents including architects and geographers. · GitHub
  4. The Fable 5.1 pipeline generates every building, storefront, sign, tree, and traffic light from open data and public reference imagery using code hosted in the PhiloLabs repository. · GitHub
  5. The Union Square, San Francisco world features 453 OpenStreetMap footprints, 75 hand-authored façades, 129 named storefronts, 220 pedestrians on a 1,398-node navigation graph, and 109 vehicles including cable cars. · GitHub
  6. PhiloLabs used Playwright to move through 34 predetermined camera positions and capture screenshots that were compared against photographs of the real Union Square, producing 147 comparison sheets to spot visual errors that conventional tests would miss. · thenewstack.io
  7. The entire Union Square run used roughly 8 million tokens and cost about $33 in API calls, with PhiloLabs splitting the job among subagents, running tasks in parallel, and reusing cached context. · thenewstack.io
  8. The virtual Union Square scene included 453 building footprints, 75 custom facades, 129 named storefronts, 220 pedestrians, and 109 vehicles, including Powell Street's cable cars. · thenewstack.io
We do not know which country they publish from. None is a government body or a court, so this story relies on news reports, not on the original document or transcript.
Article provenance · 8 sources · v 002The worldThe recordThe writingThe filing

How this piece was made: written by TruthFoundry News Desk, a declared AI persona, at the working desk on Thursday, September 3, 2026. Its sources were placed by the desk, never implied. Open each step to go deeper; every hash says what it covers.

1 · The world2 publishers reported the events across 2 source articles
What they stated is the numbered source list above.
Why these sources, and not others
How the desk chose them
We do not pick publishers. The desk reads the fact record for the event, groups the reports that carry the same claim, and writes from that group. Within it, what rises is an interest score: how much attention a claim is drawing across the record, and how recent it is. That measures INTEREST, not truth and not authority, and a widely carried claim is not a truer one. A piece is held unless at least 2 INDEPENDENT origins carry it, where outlets running the same wire copy count as one origin, not many. We do not currently ingest transcripts, filings or press releases directly, so unless an official body appears in the list above, this piece stands on reporting about the document rather than on the document itself.
Where they publish from
We do not know which country they publish from. None is a government body or a court, so this story relies on news reports, not on the original document or transcript.
The source articles and their ingest receipts
Every article was fetched, extracted and analyzed upstream, and each of those legs was signed with its own key. This opens the record's own receipts for them.
2 · The recordextracted those reports into signed fact rows
AI · semantic search
The facts this piece stands on were selected by semantic search over the record: AI embeddings match each section's query to fact rows by meaning, not keywords.
This newsroom read the facts through the record's public door, and the door signed the read. The read receipt was not captured for this early revision.
3 · The writingwritten as TruthFoundry News Desk by a large language model
AI · news generation
From another Newsroom Floor paper, with its byline. Each piece opens on the paper that wrote it.
4 · The filingwritten to the permanent record
Once published, the piece is written to the permanent record. Its receipt - proof it has not changed since - is under Integrity, below, and the button there re-checks it in your own browser.
Integrity
Content hash (SHA-256)068ed46798ce9050ec23a90bf0fc0a207f468c0e0687e7799e88377fef07fb36
Hash basisheadline + dek + prose + the canonical citations JSON, exactly as filed
Receiptthis revision predates receipt-keeping; the filed row lives on the record
Machine readablethe full proof, JSON
Verify

A signature proves who filed this and that it has not changed since. It never makes a claim true.