Act on David's editorial review: disambiguate "model", canonical chat URL - #7
Merged
Conversation
"Model" carried two meanings and collided — the language model and the PolicyEngine microsimulation, sometimes a clause apart. "The tools UK Chat exposes to the model" sat near "run through the model to produce taxes, benefits, and net income" and "reports what the model calculates". Adopted the convention he proposed: "language model" for the LLM, "the engine" or "PolicyEngine UK model" for the microsimulation, and no bare "model" where either could be meant. All 27 uses are now qualified, including the boundary diagram's accessible description and the section heading. Also his point on the engine reference, which was accurate but dense: it now reads "a machine-readable description of what the deployed engine can compute: its capabilities and parameter schema", keeping the load-bearing point that it is tied to the deployed version rather than a drifting prompt. The call to action now points at policyengine.org/uk/chat rather than the vercel.app host, which is the canonical URL both David and Max asked for. Note that route ships with PolicyEngine/policyengine-app-v2#1073 and 404s until then. The Markdown copy is regenerated to match. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Acts on David's editorial review of PolicyEngine/policyengine-app-v2#1073, applied to the page that actually ships rather than the markdown post it reviewed.
His #2, the "model" collision — the highest-value item, and correct. The word carried two meanings and they sat close together: "The tools UK Chat exposes to the model" (the LLM) near "run through the model to produce taxes, benefits, and net income" and "reports what the model calculates" (both PolicyEngine). Adopted the convention he proposed — "language model" for the LLM, "the engine" or "PolicyEngine UK model" for the microsimulation, never bare "model" where either could be meant. All 27 uses are now qualified, including the boundary diagram's accessible description and the section heading, which is now "The language model proposes a plan".
His #6, on the engine reference. Accurate but dense on first read. Now: "a machine-readable description of what the deployed engine can compute: its capabilities and parameter schema", keeping the load-bearing point that it is tied to the deployed version rather than a hand-written prompt that drifts.
One canonical chat URL — the call to action points at
policyengine.org/uk/chatinstead of thevercel.apphost, which is what both David (#7) and Max asked for. That route ships with app-v2#1073 and 404s until it merges, so the two need to land together.Already resolved before this review, so no change needed: "tool surface" jargon (#5) is gone, "excited to announce" (#1) and "pairs the language strengths" (#3) are not on the page, the GPT-5.5 model name is dropped and the 80.3% figure was verified against the PolicyBench source (#8), and the title now matches across the page and
apps.json(#9).The Markdown copy is regenerated to match.
bun run checkpasses.