What I've been building

Starting an evaluation run used to need a terminal and an account token, and now a config file loaded in the browser does it.

• You can now start a run by loading a config file in the browser, so no terminal or account token is needed.
• The panel checks the file before anything is sent and lists every problem with the field that caused it, so you fix them in one go.
• The preview shows the models, inputs, pairs to judge and how many paid model calls the run will make, so you see the cost first.
• Minting replaces whatever run is active, so it asks you to confirm before it discards a run that already has work behind it.
• You cannot start a new run while a comparison is still running, so an in-progress run keeps the models it began with.

The tools behind the site got easier to use for creating tracking links and sharing a file map, with nothing visible to visitors.

Every short link now sends visitors on as a permanent move, so Google treats the destination as the real page and, over the coming weeks, drops the short link from its results.

A sign-in fault had been sending texts to the shared number into a void for people using anecdote.

• You can now reach anecdote by texting the shared number after signing in once more, where before the text went nowhere however often you signed in.
• Identity’s database changes now go out with each deploy, so a fault like the one behind this is far less likely to slip through again.

Anecdote now takes a story by text message and holds it until you are ready to tell it properly.

• You can now text a line to anecdote, held as a note to turn into a full story later, so a memory is caught the moment it lands.
• Each texted note gets one message back confirming it, with a link that opens the story ready to finish.
• The log now opens on what you still owe, grouped under reminders and stories waiting, so nothing texted in gets lost.
• The capture screen lists your waiting notes above the box, and tapping one fills it in ready to send.
• Notes you never tell clear themselves after two weeks, and binned ones a day later, so the list stays current.
• Replies in a text conversation now come back faster, because each turn makes fewer trips to the database.

None of this touched a live app; it set up an internal run to check whether a model costing a fifth as much writes restart-a-habit steps as well.

The site had nothing for a search engine or a link preview to work with, and that has been put right.

• You can now share a link to the site and get a card with a title, description and image, where before it was a bare URL.
• Search engines can now index the site through a sitemap and structured data, so it shows up properly in results instead of as a bare domain.
• Fixed a mistyped address showing a silent copy of the homepage instead of a not-found page, and the build log skipping some days.

The shared service behind the text and voice apps got faster and sturdier, with nothing new to see on screen.

• Replies to a text message or a spoken story now come back sooner, because the service checks its spending limits in one database trip instead of three.
• Your daily usage count stays accurate now, where before a half-finished write could leave it stuck too high or too low.
• Groundwork went in so a text from an Anecdote user can be saved as a quick note instead of a task, though nothing replies to it yet.

Nothing looks different, but signing in now records which apps a person uses, so other apps can tailor what they send without a separate lookup.

Anecdote now reads and writes from a database hosted in the Oceania region rather than North America, which should trim a little delay for local users.

The model comparison tool now points at its database in a new region, with the old data copied across and verified as an exact match first.

The planner’s preview database was rebuilt in a new region and reconnected, with nothing that touches the live app you use.

The database behind the shared gateway was copied to a new region and both the live and preview services now point at it, with nothing that changes how the apps work for you.

The database behind sign-in moved to a new hosting region, with its data copied across and verified as an exact match, and nothing you do to log in changed.

The URL shortener now reads from a database in the Oceania region, copied and checked against the old one before the switch, with nothing visible changing for you.

Anecdote’s story-capture conversations now run on a different model, chosen by testing candidates on real captures.

• The new model was picked for the quality of its probing questions and story summaries, judged blind against cost and speed.
• Work was mapped out to let you text a quick note to anecdote and finish telling the story later in the app.
• Fixed story capture failing with an error and never completing, which broke new captures for everyone right after the model change.

None of this touched a live app; it was internal work letting the apps use OpenRouter chat models, and closing a way to dodge spend limits.

None of this touched a live app; it was work on the shared service that every app routes its paid calls through.

• Apps can now call any OpenRouter language model by name, without a new release of the shared service, so trying a different model is a config change.
• Language-model spending is now capped in dollars per person each day, so a costly model cannot quietly drain the whole day’s budget.
• The routes that spend money are no longer reachable from the public internet, closing a way for a stranger to run up spend against an account.
• Running the apps on a developer’s machine no longer makes real paid calls, because recorded replies now stand in for the language model.
• Fixed failed language-model calls being impossible to diagnose, because only the status code was kept and never the reason the vendor gave.