A page for the argument the language is built on - #42
Merged
Conversation
`deed mcp` was one paragraph on the install page, which is the wrong place: a person deciding whether to wire a compiler into an agent is not reading a download page. This is that paragraph turned into somewhere to be pointed at. Everything it claims about what an agent receives, it demonstrates. The four transcripts are filled in from the pinned artifact in the reader's tab, for the programs printed above them, so nothing on the page is a sample output written here. That rule already covers the playground and the diagnostics index; it matters more on a page whose whole subject is what a machine gets back. What they show, in order: - an obligation line carrying a tier, `proven` and `tested` in the same answer, neither of them asked for; - the same refinement without the precondition that establishes it, coming back `guarded` with a reason a model can act on; - the `export` diagnostic, with a machine-applicable edit and the note saying why the word does not exist, which was the single most common thing said across five recorded runs; - `deed_test` running a property generated from a contract, in a module with no tests in it. The benchmark is here as a table with the control arm beside it, and as a link to the record rather than a copy of it, along with the three things it does not establish. A page that quotes a measurement without its caveats is worse than one that quotes nothing. `assets/agents.js` carries the same `TAG` and `VERSION` as the other two scripts, so `tools/check.mjs` holds it to the pin like the rest. Nav gains a sixth entry on all six pages, and the landing page a fourth card.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
deed mcphad one paragraph, on the install page. That is the wrong place: aperson deciding whether to wire a compiler into an agent is not reading a
download page. This turns it into somewhere to be pointed at.
Everything it claims, it demonstrates
The four transcripts are filled in from the pinned artifact in the reader's
tab, for the programs printed above them. Nothing on the page is a sample
output written here. That rule already covers the playground and the
diagnostics index, and it matters more on a page whose whole subject is what a
machine gets back.
In order, the page shows:
provenandtestedin the sameanswer, neither of them asked for;
guardedwith"reason": "nothing narrowed this name", which is a sentence amodel can act on;
exportdiagnostic, with its machine-applicable edit and the note sayingwhy the word does not exist — the single most common thing said across the
five runs in
benchmarks/RESULTS.md, forty-five times;deed_testrunning a property generated from a contract, in a module with notests in it.
The measurement, with its caveats attached
The benchmark is a small table with the control arm beside it — six confident
answers either way, none of the prompt-only ones compiling — and a link to the
record rather than a copy of it, along with the three things it does not
establish. A page that quotes a measurement without its caveats is worse than
one that quotes nothing.
Held by the existing checks
assets/agents.jscarries the sameTAGandVERSIONas the other twoscripts, so
tools/check.mjscompares it to the pin like the rest, and the pagehas the favicon and the mark it asks every page for.
node tools/check.mjspasses at 72 files.
Verified in a browser: all four transcripts fill in, the status line reports
Deed 0.2.9, and the nav is the same six entries with the right one active onall six pages.
Nav gains an entry on every page, and the landing page a fourth card.