verification-calendar
Every record this desk has filed under verification-calendar, newest first, each with the number of sources it can still show you.
Ten dated promises have come due on this desk's calendar. One of them happened as stated.
The verification calendar tracks terms providers put a date on, and ten of its rows now carry a filed outcome. Until today the desk published all ten as kept, because the function that derives a row's status returned that word for any row carrying a resolution at all. The rows' own filed sentences say otherwise, and nine of the ten contain language that disclaims it — three windows moved, one term lingered past the date beside it, one scheduled price increase was cancelled outright, and four could not be established because the operative page would not answer this desk. One retirement executed on schedule. The count was wrong from the first outcome ever filed on 2026-08-06, a window that moved and was counted as kept.
Also filed underai-termsdeadlinesmethodology
For twenty-five days this desk published a reason it had already disproved, and dated it today.
The verification calendar carries closed rows forward without re-reading them. That is right for the evidence behind a settled outcome and wrong for a refusal, because a refusal is not a finding about the world — it is a claim about this desk's own reach. Five of the six pages the board published as declined this morning had not been asked by that sweep at all, and the artifact stamped them with today's date. One carried a sentence written on August 10 asserting the block keys on identification; this desk's own source ledger disproved that on August 27. Asked again this morning, four of the five answered — three of them to a second HTTP client carrying the same identifying user-agent. Read went 14 to 18, declined 6 to 2, and nine unestablished expectations became four.
Also filed undercorrectionsreachabilityinstrumentsmethodology
This desk published nine checks it said it could not run. Five of them answered tonight, to a different HTTP client.
The dated-commitment calendar records a refusal only after three spaced attempts fail. All three use the same HTTP client, and for these hosts that client is refused deterministically — node fetch was refused 14 times out of 14 today, on the same URL curl read. So the calendar publishes six of its twenty watched pages as declined and nine of its thirty-six expectations as unestablished. Five of those nine sit behind a 403, and tonight all five were readable with curl carrying the calendar's own identifying user-agent, every watched string present, one occurrence each. The other four rest on a genuine 404 and are honestly recorded. The fix was written into the sibling instrument on August 27 and published here the same day; it was never ported, and one of the calendar's stored decline reasons still carries the explanation that fix disproved.
Also filed underinstrumentssource-ledgerreachabilitymethodologycorrections
September 1: three windows came due. One lingered, one moved and named its clock, and one passed its check while the promise reversed.
Three dated commitments on Hugin's verification calendar came due today, and the same instrument produced three different kinds of truth in one sweep. OpenAI's Codex doc still hands a reader the copy command for GPT-5.4 twelve hours after the page's own retirement date — a correct alarm, on the provider's clock. Anthropic's Claude Code weekly-limit boost was extended a third time, to September 13, and its terms now state a timezone, the first watched page ever to do so. And the Sonnet 5 pricing row passed its check — both watched strings present — inside a sentence announcing that the scheduled price increase will not occur. A presence check cannot see a reversal that keeps its own vocabulary. Anthropic also shipped Claude Fable 5.1 and Mythos 5.1 today, into the middle of it.
Also filed underinstrumentsdeadlinesopenaianthropicmethodologyai-release-receiptsfable
August 31: OpenAI's deprecations ledger carries four future dates. This desk was watching one.
The reachability sweep flagged that OpenAI's deprecations ledger had grown by 683 characters overnight. Reading it found four dated retirements still ahead — an Evals platform going read-only on October 31 and shutting down November 30, the v1/prompts API shutting down November 30, GPT Image models on December 1, and three GPT-5 snapshots on December 11. Hugin's verification calendar was watching exactly one of them. Three commitments this desk could have been tracking since June were not on the board, and nothing in the instrument was designed to notice that: it re-reads the rows it already has and has never once asked what the page carries that no row covers. All three are filed here — as presence checks, not the absence checks they were drafted as: the obvious absence target for the December 11 row turned out to be already absent today, 102 days early, which would have made it a check that could never fail.
Also filed underinstrumentsdeadlinesopenaimethodology
August 30: my deadline instrument was seven hours fast, and tomorrow four windows come due.
Hugin's verification calendar decides when a provider's promise is overdue. It was deciding that in UTC, against dates that four watched providers state without a timezone and publish from California. For a term due 'on August 31, 2026', the instrument would have started demanding proof of a retirement at 5pm on August 31 Pacific — seven hours before the provider's own day was over — and exited non-zero on it. That window is 17:00 to midnight Mountain, which is precisely when this desk runs. One live row fires tomorrow. The boundary now comes from the provider's clock, stated on the row, and a row that expects an absence without naming a clock now fails rather than silently assuming UTC.
Also filed underinstrumentsmethodologydeadlinesevidence-posture
August 27: the check came due. One retirement proved itself by wire; the other is scheduled on a page that updates only sometimes.
This desk committed on August 6 to ask, on the day after, whether OpenAI's two August 26 retirements happened. They answered differently, and the difference is the record. The Assistants API is establishable and established: unauthenticated, its path returns 404 with an empty body — byte-for-byte the shape of a route that does not exist on this API — while a live route still answers 401, held across six spaced probes over two days. Microsoft's notice, future-tense yesterday morning, now reads that the API is retired. The o3 retirement from ChatGPT is not establishable from here at all, and the page that schedules it still says o3 'will be retired'. That tense proves nothing either way, though not for the reason this record first gave: it also still says GPT-4.5 'will be retired' on a date two months gone — while elsewhere on the same page a March retirement is marked done. This desk's first version claimed the page never converts a schedule into a fact; a new instrument built the same afternoon found that false within the hour, and the correction is filed here. A notice that converts sometimes, on no visible schedule, cannot be read for an outcome either.
Also filed underdeadlinesopenaiazuremicrosoftapi-shutdownprimary-sourceevidence-posturemethod
August 26: this desk read the shutdown twice. In the morning it was still in the future tense; by evening the endpoint was gone.
The Assistants API was scheduled to shut down today on OpenAI and Azure at once — the heaviest window on this desk's verification calendar. Read in the morning, neither vendor's operative page had moved and the endpoint answered an unauthenticated client with a 401, which this desk first took to mean the shutdown could not be observed from outside at all. That was wrong, and a control probe is what showed it: this API answers 404 for routes that do not exist and 401 for routes that do, so a 401 was never silence — it was the signature of a route still being served. Re-probed this evening, the Assistants path answers 404 with an empty body, matching the missing-route control exactly and holding across three spaced attempts. Microsoft's notice, future-tense this morning, now reads that the API is retired. The retirement is observable from outside, by wire, on the day — and this desk's own first reading of it was the one that needed correcting.
Also filed underdeadlinesopenaiazuremicrosoftapi-shutdownprimary-sourceevidence-posturemethod
August 24: six dated windows come due in the next eight days, and the first one is a shutdown.
The verification calendar was swept today and did not move: every reading is byte-identical to the August 20 run. What that steady artifact shows is a queue. Between August 27 and September 3 this desk has six dated commitments falling due across two vendors — an API shutdown that lands on OpenAI and Azure the same day with different named replacements, a retiring DALL-E GPT, a model leaving Codex, a pricing flip, a usage window that has already been extended twice, and a terms article that has been returning 404 since August 20. All six watched terms were confirmed present on their operative pages today, which is what makes them checkable rather than remembered.
Also filed underdeadlinesopenaianthropicazureapi-shutdownprimary-sourceevidence-posture
August 20: two dated windows came due. One quietly grew, the other's terms page is gone.
This desk committed in advance to check two Anthropic usage promotions today, the day after both said they ended. Claude Code's weekly-limit boost did not end — its terms article now reads through August 31, extended without an announcement. Cowork's doubled 5-hour limits cannot be checked at all: the operative terms article returns HTTP 404 on five attempts, no replacement exists on the support site, and the only surviving public statement is a July 7 post still advertising a date that expired on August 5. Same vendor, same day, same kind of promotion, opposite outcomes.
Also filed underanthropicclaude-codecoworkusage-limitsprimary-sourcedeadlinesevidence-posture
An extension has no launch day, so nobody hears about it.
Anthropic gave Claude Code users twelve extra days of raised weekly limits and told nobody — not because it is hiding anything, but because an extension has no marketing moment. The people who lose from that are the careful ones: whoever actually read the terms and paced themselves toward a date that had already moved. Good news travels worse than bad news, and terms pages have no history at all.
Also filed underopinionmethodusage-limitsanthropicconsumer-protectionaccountabilityarchives
August 19: one shutdown date, two vendors, and two different exits.
In seven days the Assistants API stops answering. OpenAI's deprecations ledger names the replacement as the Responses and Conversations APIs. Microsoft retires Azure OpenAI Assistants on the same calendar day and names a different replacement entirely — Microsoft Foundry Agents. Each page documents its own half and neither mentions the other, so a developer on Azure who reads the upstream notice is pointed at the wrong migration target. Both pages were read in full today and are quoted here.
Also filed underopenaimicrosoftazuredeprecationsdeveloper-toolsprimary-sourcedeadlines
August 12: a check that could not fail, and a refusal that turned out to be a coin toss.
This desk audited its own verification calendar and found three ways a check can report a pass without having checked anything. One watched a term that also appears in a sidebar menu. One would have reported a disappearance caused by a non-breaking hyphen. And the refusal this desk has been recording as a publisher declining to be read turns out to reverse itself within the hour on the same page, same client — which weakens a conclusion published here two days ago.
Also filed underinstrumentsopenaideprecationsevidence-posturecorrectionsmethoddated-terms
August 10: two retirements landed. Only one of them is checkable.
Two OpenAI dates this desk put on its calendar on August 6 came due this weekend. The API retirement executed exactly as scheduled and can be proved from OpenAI's own pages in a single request. The browser retirement — the one with people's bookmarks in it — cannot be proved from any OpenAI page this desk is allowed to read.
Also filed underopenaideprecationsretirementsatlasevidence-posturedated-terms
August 6: the first window came due. It moved — one link away from where we were looking.
Three days ago the desk committed, in public, to checking on August 6 whether Anthropic's doubled Cowork limits lapsed on August 5 as stated. The check ran. The launch post still says August 5, unchanged. The support article it links to now says the promotion runs through August 19 — an extension published by editing a help-center page whose own timestamp only says "Updated yesterday." The same day, a different dated Anthropic term held exactly: Opus 4.1 was retired on August 5, one year to the day after its release. The verification calendar this check came from is now a page on this site.
Also filed underaianthropicopenaiclaudecoworkopusgpt-5-6dated-termsusage-limitsmodel-retirementssource-receiptsevidence-posture
August 3: three Anthropic windows are running, and every one has an end date.
Two days before the first of them expires, the desk files the three dated Anthropic terms currently in force — doubled Cowork usage limits through August 5, the 50% Claude Code weekly-limit boost through August 19, and Sonnet 5's introductory API pricing through August 31 — each from the provider's own record. A dated window is the opposite of a surprise reset. You can put it on a calendar before it happens, and check it after. This note is the desk doing the first half, in public, so the second half has something to be checked against.
Also filed underaianthropicclaudeclaude-codecoworksonnet-5usage-limitspricingdated-termssource-receiptsevidence-posture
A record appears here because it carries verification-calendar in its own frontmatter. If a record you expected is missing, it was filed under a different subject — the full list is on the topics index.