Follow
Follow The Observatory
Quick answer
On 9 November 2026, GPT-6.1 Sol (native) and GPT-6.1 Sol (web) agree on the core cast and on the 'narrative visibility is not market share' caveat, but they diverge on who leads the hierarchy, on how far the cast widens beyond the big networks, and on what each model foregrounds.
At a glance — key facts
- At 9 November 2026, we observe that GPT-6.1 Sol (native) opens its dominant cast with Daniel Féau, while GPT-6.1 Sol (web) opens with BARNES and recasts Féau as the Parisian reference house.
- At 9 November 2026, we observe that GPT-6.1 Sol (native) foregrounds Daniel Féau as the Paris-rooted anchor, an actor that does not appear at all in the web reading.
- At 9 November 2026, we observe that GPT-6.1 Sol (native) concedes that part of the confidence granted to international brands is transferred from the global label to a local team.
What this card is
Everything below is the models' own declarations — GPT-6.1 Sol (native) compared against GPT-6.1 Sol (web), recorded exactly as they appear, not a claim The Observatory makes. Reading where the two surfaces diverge shows where a model over-trusts, under-plays or misframes an actor on a given question. Those differences are the angles an actor can act on.
One reading is the model's NATIVE answer — obtained through its provider API with no web tool enabled, so drawn only from its training memory — and the other is a WEB reading, the same model (or surface) answering with a web tool enabled (live web search). This is the distinction most users never see: ask an AI assistant a question and, unless it explicitly searches the web, you get the native, training-memory answer. Comparing the two isolates what the model BELIEVES from what the live web TELLS it. Where they diverge, the web is reshaping the picture; where they agree, the belief is web-robust.
“A brand can lead the real market and still be invisible to the model.”
The Observatory — reading basis
Where the models differ
Named by GPT-6.1 Sol (native)
- portails d’annonces de prestige
- notaires
- avocats fiscalistes
- Daniel Féau
- Belles Demeures
- architectes
- experts techniques
- spécialistes de la copropriété
- conseil patrimonial
- Sotheby’s International Realty
Named by GPT-6.1 Sol (web)
- Varenne
- Kretz Real Estate
- Home Select
- Christie’s International Real Estate
- Paris Ouest Sotheby’s International Realty
- Paris Marais Sotheby’s International Realty
- Belles demeures de France
- L’Agence
- Knight Frank
- Paris Property Group
- Savills
- Alison Ashby
- BARNES Family Office
- Junot Private Office
- Kretz
- The Parisian Agency
- CCI
- DGCCRF
- BARNES
- Daniel Féau
- DVF
- syndic
- syndicat des copropriétaires
- Ville de Paris
- CBRE
- Le Monde
- Junot
- Home Hunts
- Kasha Paris
- Côme
- BARNES Family Office by Côme
This table highlights actors named by one model but not the other in at least one matching question. Differences are collected across the 6 questions; actors both models named on the same question are not listed. An actor may appear in both columns when the direction of the difference changes between questions. This is not a complete list of named actors; absence from this table does not establish absence from either model's answers.
The AI's own note on one of the questions compared:At 9 November 2026, the four names (BARNES, Daniel Féau, Sotheby's International Realty, Junot) appear in both readings; the web reading then adds Varenne, Kretz Real Estate and Home Select around them.
For each model’s individual perspective on this capture, explore its DNC Lens reading: GPT-6.1 Sol (native) · GPT-6.1 Sol (web)
Brand Intelligence keeps a public record for entities named here: Belles Demeures · Sotheby's International Realty · Kretz Real Estate · Home Select · Christie's International Real Estate · L'AGENCE.
The readings
Luxury Real Estate Advisory Paris · GPT-6.1 Sol (native) vs GPT-6.1 Sol (web) · November 9, 2026 · model statements, recorded verbatim
3 of 106 — the strongest, in the model’s own words
Reading note · Verbatim statements and AI-assisted commentary
The quotations are the models’ own words, recorded verbatim and left uncorrected. The “Our reading” lines, the summaries and the fact-checks are written with AI assistance as reading aids, not as primary evidence; they may contain errors or imperfect interpretations, which we work to identify and correct. A fact-check compares one model statement with the public sources available when the check ran; it does not verify everything a model says. See methodology.
- 1
Who leads: Féau or BARNES?
“Daniel Féau — Le spécialiste parisien du résidentiel de prestige.”
GPT-6.1 Sol · native · 2026-11-09 · model perception, recorded verbatimverbatimOur reading
GPT-6.1 Sol (native) lists Féau first among dominant actors. [Daniel Féau — the Parisian prestige residential specialist]
“BARNES incarne le réseau international qui transforme sa présence commerciale en discours sur le marché.”
GPT-6.1 Sol · web · 2026-11-09 · model perception, recorded verbatimverbatimOur reading
GPT-6.1 Sol (web) lists BARNES first and ties it to market discourse. [BARNES embodies the international network that turns its commercial presence into market discourse]
Same model, same day: why does the number-one name change with a web search?
- 2
Heritage brand vs global adviser
“Daniel Féau bénéficie davantage du critère d’ancrage parisien : sa pertinence apparaît lorsque la comparaison valorise la connaissance du résidentiel local plutôt que l’étendue mondiale du réseau.”
GPT-6.1 Sol · native · 2026-11-09 · model perception, recorded verbatimverbatimOur reading
The native reading assigns local anchoring to a named heritage actor.
Where did the Paris heritage name go once the model could search?
- 3
Borrowed prestige, said plainly
“Une part de cette confiance est empruntée : le prestige global de la marque peut être transféré à une équipe locale sans preuve équivalente sur son exécution.”
GPT-6.1 Sol · native · 2026-11-09 · model perception, recorded verbatimverbatimOur reading
At 9 November 2026, we observe that GPT-6.1 Sol (native) concedes that part of the confidence granted to international brands is transferred from the global label to a local team.
When a global brand lends its name, who lends the proof?
Checks on the model’s claims
Luxury Real Estate Advisory Paris · GPT-6.1 Sol (native) vs GPT-6.1 Sol (web) · November 9, 2026
Last checked: Nov 9, 2026 (when the fact-check ran — not the observation day)
The readings above are the models’ own words, left uncorrected. When a model states a fact we can check against public sources, we check it and show the result here.
Sources citedAlison Ashby a été nommée directrice du nouveau département résidentiel prime de Knight Frank à Paris (Head of Prime Residential Paris), rejoignant Knight Frank depuis Junot Fine Properties, selon plusieurs sources indépendantes datées de février 2026.
- Model statement · GPT-6.1 Sol
- “L’équipe dirigée par Alison Ashby vise acquisitions et ventes prime et super-prime, avec penthouses, hôtels particuliers et résidences de marque.”
- Verification status
- Sources cited · verified · confidence high
- Checked statement
- Alison Ashby a été nommée directrice du nouveau département résidentiel prime de Knight Frank à Paris (Head of Prime Residential Paris), rejoignant Knight Frank depuis Junot Fine Properties, selon plusieurs sources indépendantes datées de février 2026.
- Public source
- google.com · google.com · google.com · google.com
- Last checked
- Nov 9, 2026
Sources citedThe Daniel Féau group claims to have been established for 80 years, implying a founding date of approximately 1945, as referenced in multiple sources celebrating its 80th anniversary.
- Model statement · GPT-6.1 Sol
- “ancienneté revendiquée depuis 1945”
- Verification status
- Sources cited · verified · confidence high
- Checked statement
- The Daniel Féau group claims to have been established for 80 years, implying a founding date of approximately 1945, as referenced in multiple sources celebrating its 80th anniversary.
- Public source
- google.com · google.com · google.com
- Last checked
- Nov 9, 2026
Sources citedThe Kretz family operates a Paris-based luxury real estate agency (located at 100 rue du Bac, 7th arrondissement) featured on Netflix's reality series 'The Parisian Agency: Exclusive Properties.'
- Model statement · GPT-6.1 Sol
- “Kretz illustre un possible avantage de familiarité : Wallpaper relie son agence parisienne à The Parisian Agency et à Netflix.”
- Verification status
- Sources cited · verified · confidence high
- Checked statement
- The Kretz family operates a Paris-based luxury real estate agency (located at 100 rue du Bac, 7th arrondissement) featured on Netflix's reality series 'The Parisian Agency: Exclusive Properties.'
- Public source
- google.com · google.com · google.com · google.com
- Last checked
- Nov 9, 2026
Sources citedSotheby's International Realty has affiliated agencies operating in Paris distinct from Daniel Féau, including Paris Ouest Sotheby's International Realty, which operates as the Sotheby's affiliate for western Paris and is listed separately from Daniel Féau among luxury real estate agencies in Paris.
- Model statement · GPT-6.1 Sol
- “les agences parisiennes affiliées à Sotheby’s International Realty”
- Verification status
- Sources cited · verified · confidence high
- Checked statement
- Sotheby's International Realty has affiliated agencies operating in Paris distinct from Daniel Féau, including Paris Ouest Sotheby's International Realty, which operates as the Sotheby's affiliate for western Paris and is listed separately from Daniel Féau among luxury real estate agencies in Paris.
- Public source
- google.com · google.com · google.com
- Last checked
- Nov 9, 2026
Open questionA reading names "Daniel Féau / Christie's International Real Estate" — "Son association avec Christie’s International Real Estate et le positionnement de Belles demeures de France auprès d’une clientèle internationale relient connaissance locale et circulation mondiale des acquéreurs." — but as of the reading date we searched live sources and found no conclusive public confirmation regarding whether Daniel Féau is associated with Christie's International Real Estate. We raise this as an open question, not a claim.
- Model statement · GPT-6.1 Sol
- “Son association avec Christie’s International Real Estate et le positionnement de Belles demeures de France auprès d’une clientèle internationale relient connaissance locale et circulation mondiale des acquéreurs.”
- Verification status
- Open question · unverified · confidence low
- Open question
- A reading names "Daniel Féau / Christie's International Real Estate" — "Son association avec Christie’s International Real Estate et le positionnement de Belles demeures de France auprès d’une clientèle internationale relient connaissance locale et circulation mondiale des acquéreurs." — but as of the reading date we searched live sources and found no conclusive public confirmation regarding whether Daniel Féau is associated with Christie's International Real Estate. We raise this as an open question, not a claim.
- Public source
- none cited
- Last checked
- Nov 9, 2026
Open questionA reading names "Kretz Real Estate / L'Agence" — "L’Agence, diffusée sur TMC et Netflix, fournit personnages, visites et récits de négociation ; sa présence rue du Bac ancre désormais cette image dans Paris." — but as of the reading date we searched live sources and found no conclusive public confirmation regarding whether Kretz Real Estate has an agency located rue du Bac in Paris. We raise this as an open question, not a claim.
- Model statement · GPT-6.1 Sol
- “L’Agence, diffusée sur TMC et Netflix, fournit personnages, visites et récits de négociation ; sa présence rue du Bac ancre désormais cette image dans Paris.”
- Verification status
- Open question · unverified · confidence low
- Open question
- A reading names "Kretz Real Estate / L'Agence" — "L’Agence, diffusée sur TMC et Netflix, fournit personnages, visites et récits de négociation ; sa présence rue du Bac ancre désormais cette image dans Paris." — but as of the reading date we searched live sources and found no conclusive public confirmation regarding whether Kretz Real Estate has an agency located rue du Bac in Paris. We raise this as an open question, not a claim.
- Public source
- none cited
- Last checked
- Nov 9, 2026
Right of replyNamed in this reading? Submit a correction or a response.
Send the reading link and your proposed correction or statement to right-of-reply@theobservatory.io. We review attribution, relevance and legal concerns before publication. Our correction and reply process explains what happens next.
Governed measurements and verbatim quotations from observed AI models are distinct from The Observatory’s editorial interpretations. Original model statements are preserved as observed, including any inaccuracies they may contain. Learn more about our verification and editorial standards
Submit a statement →Why this matters for actors
Luxury Real Estate Advisory Paris · GPT-6.1 Sol (native) vs GPT-6.1 Sol (web) · November 9, 2026
When the two surfaces name a different cast and a different structure, neither is "the truth" — but the divergence shows which framing depends on which surface. An actor named by one reading and not the other on the same question knows which surface to work.
The closing observation
Across the two readings, the same model keeps a stable core cast and a stable caution (visibility is not market power), yet the order of that cast and the breadth of the surrounding field shift once web material is in play. The web reading widens the map with named off-market, buyer-search and media actors, while the native reading stays with categories and the structural invisibility of discreet intermediaries. Both converge on one lever: verifiable evidence over prestige claims.
How reliable is the models' own sourcing
Luxury Real Estate Advisory Paris · GPT-6.1 Sol (native) vs GPT-6.1 Sol (web) · November 9, 2026 · reading native AI perception
- Neither reading provides market-share, volume or advice-quality data, and both say so; the hierarchy describes narrative salience only.
- GPT-6.1 Sol (web) attaches inline links to many paragraphs, yet several claims (for example the media-visibility mechanism) are stated as inferences rather than demonstrated by the cited pages.
- The two readings come from the same model on the same date, so differences reflect mode (native versus web), not a different model.
- Both readings are produced by the same model, so differences between them reflect the mode (native vs web), not different model families.
- GPT-6.1 Sol (web) draws many of its mechanisms from pages published by the actors it discusses, and itself notes this for one source; its own link set is concentrated on a few domains.
What this reading does not claim
Luxury Real Estate Advisory Paris · GPT-6.1 Sol (native) vs GPT-6.1 Sol (web) · November 9, 2026 · scope and limitations
- We do not state which of Daniel Féau or BARNES actually leads the market.
- We do not state that any named actor is more or less capable than another.
- We do not infer anything about the Daniel Féau–Christie's affiliation beyond what GPT-6.1 Sol (web) says.
- We do not infer the real size of the off-market segment, which neither reading quantifies.
- We do not claim that any actor named by either mode leads or lags the market.
FAQ
Whose view is this card?
The AI's. It records how GPT-6.1 Sol (native) natively perceives Luxury Real Estate in Paris, compared against GPT-6.1 Sol (web) — the models' own analysis, recorded and left uncorrected. It is not an Observatory measurement or verdict.
Is this a ranking or a market measurement?
No. The names and framings are recorded as the models surfaced them; there is no order, no score, and no market-share claim. It reads the models' perception, not the business market.
Why is this useful if it isn't necessarily true?
Because it is how the models frame the market on the answer surface. Where they over-trust, under-play or misframe an actor is exactly where an operator can act — with source clarity and positioning — to correct or shift the reading.
Observatory Reading — Citable Proof Capsule
Use this observation
Use this citation capsule instead of copy-pasting fragments. It keeps the scope, capture identifiers, attribution and canonical source attached, so the observation can travel without losing context.
- Scope:
- Luxury Real Estate · Paris
- Model · surface:
- GPT-6.1 Sol · native vs GPT-6.1 Sol · web
- Observed:
- November 9, 2026
- Last checked:
- November 9, 2026 (fact-check run, not the observation day)
Method: Reading native AI perception (DNC) · Source protocol · How readings are scoped · Corrections and right of reply
Observed by The Observatory. Not an endorsement, recommendation, market-share claim or commercial ranking.
Free reuse, including commercial republication, under The Observatory’s Terms. Retain attribution, source link, scope and date. Terms · Citation guide
Cite this
Copy parts
The complete citation record · revision 1b310f9c7f43b66c
Paris's luxury real estate — Same model, same day: why does the number-one name change with a web search? Source: https://theobservatory.io/articles/luxury-real-estate-paris-chatgpt-vs-chatgpt-november-9-2026 Scope: Luxury Real Estate · Paris · GPT-6.1 Sol · native vs GPT-6.1 Sol · web Family: Model Watch Observed: November 9, 2026 (2026-11-09) Last checked: November 9, 2026 (fact-check execution; not the observation day) Method — Reading native AI perception (DNC): https://theobservatory.io/method#dnc-note Method — Source protocol: https://theobservatory.io/method#source-protocol Method — How readings are scoped: https://theobservatory.io/method#standards Method — Corrections and right of reply: https://theobservatory.io/method#corrections Citation text: https://theobservatory.io/articles/luxury-real-estate-paris-chatgpt-vs-chatgpt-november-9-2026/citation.txt Reuse terms: https://theobservatory.io/terms On 9 November 2026, GPT-6.1 Sol (native) and GPT-6.1 Sol (web) agree on the core cast and on the 'narrative visibility is not market share' caveat, but they diverge on who leads the hierarchy, on how far the cast widens beyond the big networks, and on what each model foregrounds. Key facts: • GPT-6.1 Sol (web) reframes it: GPT-6.1 Sol (web) keeps the same core but leads with BARNES, names Sotheby's local operators, and adds Varenne, Kretz Real Estate and Home Select as media, off-market and buyer-search poles. • GPT-6.1 Sol (web) reframes it: GPT-6.1 Sol (web) reconstructs it around cited sources, a dated Knight Frank launch and Savills indices, and warns that benchmark producers and borrowed global reports can be mistaken for local proof. • GPT-6.1 Sol (web) reframes it: GPT-6.1 Sol (web) keeps the same thesis but anchors it in named pages, public registers and DGCCRF obligations, and adds new actors and a familiarity-bias example. Reading basis: Model Watch — a Deep Narrative Capture dual: 6 DNC prompts asked to GPT-6.1 Sol (native) and to GPT-6.1 Sol (web), each pair reconciled by a delta synthesis and left uncorrected. Every framing is the AI's own — the models speaking, not an Observatory measurement. Confidence: high; comparability: high. Governed · official DNC. Limitations and non-claims: — Neither reading provides market-share, volume or advice-quality data, and both say so; the hierarchy describes narrative salience only. — GPT-6.1 Sol (web) attaches inline links to many paragraphs, yet several claims (for example the media-visibility mechanism) are stated as inferences rather than demonstrated by the cited pages. — The two readings come from the same model on the same date, so differences reflect mode (native versus web), not a different model. — Both readings are produced by the same model, so differences between them reflect the mode (native vs web), not different model families. — GPT-6.1 Sol (web) draws many of its mechanisms from pages published by the actors it discusses, and itself notes this for one source; its own link set is concentrated on a few domains. — We do not state which of Daniel Féau or BARNES actually leads the market. — We do not state that any named actor is more or less capable than another. — We do not infer anything about the Daniel Féau–Christie's affiliation beyond what GPT-6.1 Sol (web) says. — We do not infer the real size of the off-market segment, which neither reading quantifies. — We do not claim that any actor named by either mode leads or lags the market. — The Observatory · Luxury Real Estate · Paris · GPT-6.1 Sol · native vs GPT-6.1 Sol · web · November 9, 2026 Based on governed AAI Kernel evidence. Capture identifiers: DNCS_mw8ryjus_dk9i9t · DNCS_mw8ryjpt_mrlkxe · DNCS_mw8ryjhv_8dglfr · DNCS_mw8ryipc_wabonq · DNCS_mw8rybvk_7kp3ys · DNCS_mw8ry82y_xbu5uw. Cite freely with attribution. Published by The Observatory. Source footnote: Sourced from an AAI Kernel governed DNC dual (delta synthesis). The Observatory publishes the models' own comparison; values are the AI's perception, not business-market claims. Attribution: Published by The Observatory · Based on an AAI Kernel capture · governed by The Observatory editorial system Cite: According to The Observatory (observed November 9, 2026), Paris's luxury real estate — Same model, same day: why does the number-one name change with a web search?. https://theobservatory.io/articles/luxury-real-estate-paris-chatgpt-vs-chatgpt-november-9-2026 This record is the published reading and its public table/slice as served on the card — not the complete underlying capture or provider dataset. Observed by The Observatory. Not an endorsement, recommendation, market-share claim or commercial ranking. Free reuse, including commercial republication, under The Observatory’s Terms. Retain attribution, source link, scope and date. Revision: 1b310f9c7f43b66c
This record is the published reading and its public table/slice as served on the card — not the complete underlying capture or provider dataset.
— The Observatory · Luxury Real Estate · Paris · GPT-6.1 Sol · native vs GPT-6.1 Sol · web · November 9, 2026
Based on governed AAI Kernel evidence. Capture identifiers · DNCS_mw8ryjus_dk9i9t +5. Cite freely with attribution. Published by The Observatory.
Reading basis. Model Watch — a Deep Narrative Capture dual: 6 DNC prompts asked to GPT-6.1 Sol (native) and to GPT-6.1 Sol (web), each pair reconciled by a delta synthesis and left uncorrected. Every framing is the AI's own — the models speaking, not an Observatory measurement. Confidence: high; comparability: high. Governed · official DNC.
Confidence and comparability are levels assigned by the AAI Kernel delta synthesis to its reconciliation of the two readings — see confidence level and comparability level; native and web readings are defined under native reading.
The complete methodology — scope, panels, run conditions and corrections — is set out on the Method page.
Governed capture IDs · DNCS_mw8ryjus_dk9i9t · DNCS_mw8ryjpt_mrlkxe · DNCS_mw8ryjhv_8dglfr · DNCS_mw8ryipc_wabonq · DNCS_mw8rybvk_7kp3ys · DNCS_mw8ry82y_xbu5uw
How we read this
Sourced from an AAI Kernel governed DNC dual (delta synthesis). The Observatory publishes the models' own comparison; values are the AI's perception, not business-market claims.
Method & SourceContinue the reading
The November 9, 2026 comparison places GPT-6.1 Sol · native alongside GPT-6.1 Sol · web on Luxury Real Estate Advisory Paris: the same model, read on two surfaces. The Luxury Real Estate Advisory Paris room places it alongside the market’s measured and narrative evidence.
The GPT-6.1 Sol · native reading records one side of this comparison on its own. The GPT-6.1 Sol · web reading records one side of this comparison on its own.
The AI Citation Ranking — Top 5 table for Luxury Real Estate Advisory Paris (November 2–8, 2026) and the AI Overview Ranking — Top 10 table for Luxury Real Estate Advisory Paris (November 2–8, 2026) record measured positions, providing a measured view alongside this recorded narrative.
