Repository navigation
Site: history to Oct 22, test 8 agent pieces, show-don't-tell pass - #3
Merged
Merged
Conversation
- site/data/history.json: timeline, findings, tests 4/7/8, runs, A/B rows and pick updates mined from the private
bake-off for 2026-10-07 on; build_data.py merges it. The lab notebook (stopped at 10-15) is gone.
- oneshots/agent-{pagoda,orrery}: test 8 grades, the agent's final file and offline frames; played in the same
sandboxed viewer. A one-shot -> agent chart pairs each model's scores.
- Fable 5.1 cut the page's visible text by 64 % (9,906 -> 3,540 words): charts and numbers lead, details fold away.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Brings the showcase up to 2026-10-22 (mined history, tests 4/7/8, test 8 agent pagodas and orreries in the sandboxed viewer, a one-shot → agent chart) and cuts the visible text by 64 % so the charts lead. Checks: check_site.mjs and the render smoke pass; clean-context review findings fixed.