Back to the scorecard

A machine satisfies the agreed Long Bets Turing protocol.

Reference judgmentPendingDisputedResearch snapshot · October 15, 2026
Source confidence & research status
i
Editorial paraphrase · evidence v0.3. AI-assisted editorial assessments; original book editions not independently collated. Attribution and outcome confidence are recorded separately.

Source state: TEXT CONFIRMED IN LISTED SOURCE.

Attribution confidence
MEDIUM
Outcome confidence · deadline / review
HIGH / HIGH
Timing confidence / kind
LOW · UNESTABLISHED
Population
Technology markets and relevant users; no universality unless the forecast expressly requires it.

Our reading of the claim

Reference (stated reasonable reading)

Pending

Criterion: A machine passes the specific two-hour, multi-judge protocol in the Kurzweil–Kapor wager.

Deadline: 2029 · Not counted in this comparison

At original deadlineNOT DUE
By review dateNOT FULFILLED

The 2029 wager deadline is still ahead. The located evidence does not document a completed pass under that contract. Five-minute conversational studies are a different protocol.

Deadline and follow-up notes

At deadline: The 2029 wager deadline is still ahead.

By review: The located evidence does not document a completed pass under that contract. Five-minute conversational studies are a different protocol.

Evidence: P03 (opens in a new tab)O21 (opens in a new tab)

View this reading in the scorecard →
01

The forecast and its attribution.

EDITORIAL PARAPHRASE

A machine satisfies the agreed Long Bets Turing protocol.

Long Bets #1 — Kapor/Kurzweil Turing-test agreement

2002 · Attribution / year unconfirmed
Agreement and detailed Turing-test rules

PRIMARY CONTRACT

Source publication: 2002 · Access: text checked

Kapor takes the NO side; Kurzweil takes the opposing side. Detailed test conditions belong to this contract, not to every generic use of “Turing test.”

Catalogue entry P03
Open listed source (opens in a new tab)
Normalized claim
A machine satisfies the agreed Long Bets Turing protocol.
Success criteria
A machine passes the specific two-hour, multi-judge protocol in the Kurzweil–Kapor wager.
Claim type
Capability
02

Timeline

PREDICTION MADE2002Attributed forecast year; original edition not collated
ORIGINAL TARGET2029Deadline supplied by this assessment
FULL REALIZATION—No achievement year established

UNESTABLISHED: Deadline not yet reached

Outcome at original deadlineNOT DUE
Outcome at reviewNOT FULFILLED

Supplied target wording: 2029. The original deadline is preserved if a later forecast revises it. Forecast horizon: not established. Drift is a calendar-year difference, not a precise elapsed duration.

03

The evidence.

CONTEXT · Publication date not recorded

Long Bets #1 — Kapor/Kurzweil Turing-test agreement (opens in a new tab)

Kapor takes the NO side; Kurzweil takes the opposing side. Detailed test conditions belong to this contract, not to every generic use of “Turing test.”. Kapor takes the NO side; Kurzweil takes the opposing side. Detailed test conditions belong to this contract, not to every generic use of “Turing test.”

Source checked as of 2026-10-15
PRIMARY CONTRACT

Source publication: 2002 · Access: text checked

Kapor takes the NO side; Kurzweil takes the opposing side. Detailed test conditions belong to this contract, not to every generic use of “Turing test.”

Catalogue entry P03
CONTEXT · 2025-03-31

Large Language Models Pass the Turing Test — Jones and Bergen (opens in a new tab)

Five-minute experimental protocol. GPT-4.5 with a humanlike persona was judged human in 73% of the reported comparisons. Not the two-hour Long Bets protocol.. Five-minute experimental protocol. GPT-4.5 with a humanlike persona was judged human in 73% of the reported comparisons. Not the two-hour Long Bets protocol.

Source checked as of 2026-10-15
PRIMARY RESEARCH PAPER

Source publication: 2025-03-31 · Access: reused checked source

Five-minute experimental protocol. GPT-4.5 with a humanlike persona was judged human in 73% of the reported comparisons. Not the two-hour Long Bets protocol.

Catalogue entry O21

Capability, adoption, and timing

A related breakthrough is not automatically fulfillment. Review must check the actual capability, how widely it was required to be used, the specified technology, and the original deadline. A prototype cannot establish a claim about routine or widespread use.

i
Alternative interpretation: Assessment is conditional on the stated criterion and population. Documented examples establish availability, not universal adoption. The original book edition has not been independently collated.
04

Research notes & history

Assessment is conditional on the stated criterion and population. Documented examples establish availability, not universal adoption. The original book edition has not been independently collated.

Imported from
kurzweil_verification_v0_3_package/predictions.canonical.v0.3.json
Legacy identifier
None
Forecast family
F-TURING
Parent statement
Not assigned
File checksum
93ae54d9ea2f1bd1817c481b85e2b707812bcd934c74d0f1715fa098d9b5f51b
Inspect preserved source fields
release_record
{"population_scope":"Technology markets and relevant users; no universality unless the forecast expressly requires it.","attribution_confidence":"MEDIUM","interpretation_confidence":"MEDIUM","outcome_confidence":{"at_deadline":"HIGH","at_review":"HIGH"},"timing_confidence":"LOW","date_uncertainty_affects_verdict":false,"interpretations":{"reference":{"criterion":"A machine passes the specific two-hour, multi-judge protocol in the Kurzweil–Kapor wager.","at_deadline":"NOT_DUE","at_review":"NOT_FULFILLED","rationale":"The 2029 wager deadline is still ahead. The located evidence does not document a completed pass under that contract. Five-minute conversational studies are a different protocol.","relaxed_or_changed_conditions":[],"kind":"REFERENCE_READING","documented_by_year":null,"at_deadline_rationale":"The 2029 wager deadline is still ahead.","at_review_rationale":"The located evidence does not document a completed pass under that contract. Five-minute conversational studies are a different protocol.","evidence_source_ids":["P03","O21"],"verdict":"PENDING","same_as_reference":false,"eligible_for_deadline_metrics":false,"deadline_year":2029,"outcome_assessment_complete":true},"strict":{"criterion":"A machine passes the specific two-hour, multi-judge protocol in the Kurzweil–Kapor wager.","at_deadline":"NOT_DUE","at_review":"NOT_FULFILLED","rationale":"The 2029 wager deadline is still ahead. The located evidence does not document a completed pass under that contract. Five-minute conversational studies are a different protocol.","relaxed_or_changed_conditions":[],"kind":"REFERENCE_READING","documented_by_year":null,"at_deadline_rationale":"The 2029 wager deadline is still ahead.","at_review_rationale":"The located evidence does not document a completed pass under that contract. Five-minute conversational studies are a different protocol.","evidence_source_ids":["P03","O21"],"verdict":"PENDING","same_as_reference":true,"eligible_for_deadline_metrics":false,"deadline_year":2029,"outcome_assessment_complete":true},"broader":{"criterion":"A machine is judged human in a controlled short conversational imitation test.","at_deadline":"NOT_DUE","at_review":"FULFILLED","rationale":"The 2025 study supports this relaxed test. It does not settle the contract.","relaxed_or_changed_conditions":["Two-hour interviews and contractual judging conditions"],"kind":"ALTERNATIVE_READING","documented_by_year":2025,"evidence_source_ids":["P03","O21"],"verdict":"CORRECT","same_as_reference":false,"eligible_for_deadline_metrics":false,"deadline_year":2029,"outcome_assessment_complete":true}},"timing":{"first_full_achievement_year":null,"documented_by_year":null,"achievement_interval_years":null,"kind":"UNESTABLISHED","label":"Deadline not yet reached","drift_years":null,"drift_range_years":null},"deduplication":{"is_canonical":true,"is_repeated_identical_claim":false,"counting_unit":"DISTINCT_FORECAST_VERSION","note":"Different deadlines or materially different thresholds remain separate versions; identical legacy repetitions are linked, not recounted."},"revision_history":[{"from_version":"0.2","previous_assessment":{"review_state":"ASSESSED","verdict":"PENDING","as_of":"2026-10-14","at_deadline":"NOT_DUE","at_review":"NOT_ASSESSED","confidence":"MEDIUM","disputed_interpretation":false,"benchmark_ready":true,"rationale":"The 2025 Jones/Bergen experiment used five-minute conversations. It is important evidence about conversational imitation but does not by itself settle this different contract.","first_full_achievement_year":null,"full_achievement_documented_by_year":null,"drift_years":null,"drift_range_years":null,"still_unfulfilled_as_of_review":false,"eligible_for_deadline_metrics":false,"withheld_reason":"Future, unresolved, intrinsically unscorable, or interpretation-dependent; see assessment."},"change_reason":"Complete deadline/current outcome assessment under explicit scope; separate uncertainty from verdict."}],"is_new_in_v03":false,"counting_policy":{"unit":"distinct_forecast_version","identical_repetitions_count_once":true,"alternative_interpretations_count_once":true,"legacy_conditional_rows_count":false},"id":"K023","slug":"k023-the-specific-kurzweil-kapor-turing-test-wager","title":"The specific Kurzweil–Kapor Turing-test wager","prediction_paraphrase":"A machine satisfies the agreed Long Bets Turing protocol.","wording_kind":"EDITORIAL_PARAPHRASE","original_quote":null,"primary_category":"AI & software","tags":["contract","benchmark"],"subcategory":"Turing test","claim_type":"CAPABILITY","family_id":"F-TURING","parent_statement_id":null,"legacy_ids":[],"origin":"ADDED_PRIMARY_SOURCE","publication":{"forecast_year":2002,"year_basis":"SOURCE_PUBLICATION","original_book_edition_checked":false,"forecast_year_status":"SUPPORTED_BY_LISTED_SOURCE"},"target":{"text":"2029","deadline_year":2029,"precision":"YEAR","year_start":2029,"year_end":2029,"interpretation":null},"source_verification":{"state":"TEXT_CONFIRMED_IN_LISTED_SOURCE","confidence":"MEDIUM","book_text_not_independently_collated":false},"success_criteria":"A machine passes the specific two-hour, multi-judge protocol in the Kurzweil–Kapor wager.","assessment":{"at_deadline_rationale":"The 2029 wager deadline is still ahead.","at_review_rationale":"The located evidence does not document a completed pass under that contract. Five-minute conversational studies are a different protocol.","verdict_qualifier":null,"outcome_evidence_basis":"DIRECT_AND_CONTEXTUAL_EVIDENCE_WITH_EXPLICIT_EDITORIAL_INTERPRETATION","attribution_is_separate":true,"first_event_date_required_for_verdict":false,"at_review_semantics":"FULL_REALIZATION_HAS_OCCURRED_BY_REVIEW_NOT_NECESSARILY_CURRENT_PRODUCT_SALES","review_state":"EDITORIAL_ASSESSMENT_COMPLETE","verdict":"PENDING","as_of":"2026-10-15","at_deadline":"NOT_DUE","at_review":"NOT_FULFILLED","confidence":"HIGH","disputed_interpretation":true,"benchmark_ready":false,"rationale":"The 2029 wager deadline is still ahead. The located evidence does not document a completed pass under that contract. Five-minute conversational studies are a different protocol.","first_full_achievement_year":null,"full_achievement_documented_by_year":null,"drift_years":null,"drift_range_years":null,"still_unfulfilled_as_of_review":true,"eligible_for_deadline_metrics":false,"withheld_reason":"Future deadline; current progress nevertheless assessed."},"prediction_sources":[{"source_id":"P03","locator":"Agreement and detailed Turing-test rules","role":"FORECAST_ATTRIBUTION"}],"evidence":[{"source_id":"P03","locator":"Kapor takes the NO side; Kurzweil takes the opposing side. Detailed test conditions belong to this contract, not to every generic use of “Turing test.”","role":"OUTCOME_EVIDENCE"},{"source_id":"O21","locator":"Five-minute experimental protocol. GPT-4.5 with a humanlike persona was judged human in 73% of the reported comparisons. Not the two-hour Long Bets protocol.","role":"OUTCOME_EVIDENCE"}],"limitations":"Assessment is conditional on the stated criterion and population. Documented examples establish availability, not universal adoption. The original book edition has not been independently collated.","open_questions":[],"legacy_relations":[{"legacy_id":"AUD-024","relation":"LINK_FAMILY_NOT_EXACT_DUPLICATE"},{"legacy_id":"DEC-027","relation":"LINK_FAMILY_NOT_EXACT_DUPLICATE"},{"legacy_id":"EXE-020","relation":"LINK_FAMILY_NOT_EXACT_DUPLICATE"},{"legacy_id":"EXE-011","relation":"QUARANTINE_AND_SPLIT_REQUIRED"}]}

Review history

— Evidence v0.2: PENDING. The 2025 Jones/Bergen experiment used five-minute conversations. It is important evidence about conversational imitation but does not by itself settle this different contract. Change: Complete deadline/current outcome assessment under explicit scope; separate uncertainty from verdict.

— Evidence v0.3: EDITORIAL_ASSESSMENT_COMPLETE; supplied verdict PENDING. The 2029 wager deadline is still ahead. The located evidence does not document a completed pass under that contract. Five-minute conversational studies are a different protocol.

Related forecasts.

K045Hardware and software achieve human-level intelligence.