A

Running

A / prompts

257 kB

Ctrl+K

1 contributor

explain-rationale Path 3: rewrite triggers to be semantic intent (not keyword phrase match) - illustrative phrases marked non-exhaustive, intent test added

85f1e6c verified about 1 month ago

main_prompt.md

28.5 kB
main: add 2 scratch verify fields (msg_break + on_the_right_count) on transition-due to nudge bot to check Block 1 rendering about 1 month ago
manager_prompt.md

188 kB
explain-rationale Path 3: rewrite triggers to be semantic intent (not keyword phrase match) - illustrative phrases marked non-exhaustive, intent test added about 1 month ago
paraphrase_prompt.md

7.37 kB
UI hotfix: restore aha!/ugh. buttons. The previous top-chrome-hide CSS included '.icon-button-wrapper { display: none }', but Gradio uses that same wrapper class for the repurposed Like/Dislike (aha/ugh) buttons in the message footer, so they disappeared along with the share/clear toolbar buttons. Drop the wrapper rule and rely solely on aria-label / title matchers for share/clear/delete/trash. about 2 months ago
perfect_answer_prompt.md

33.1 kB
STEP 1 framework detection: mixed-drafts rule refined. Previous version of new STEP 1 hard-defaulted mixed drafts to consequence, which misclassified Kantian-explicit arguments that listed multiple harms before naming agency as the core (consistency went down from 7/9 to 3/5 on the pilot Kantian argument). Refined rule: when 2+ frameworks are load-bearing, pick the participant's CORE argument by (1) explicit emphasis markers like 'the most important reason' / 'the thing that is most ethically questionable is X' / 'perhaps for me' (highest priority), (2) argumentative weight (the most-defended claim), (3) 'remove the lens' decisive test. Consequence is only a last-resort default for genuinely balanced drafts with no detectable core. Re-tested: 5/5 Kantian argument now correctly → duty_rights (up from 3/5). about 2 months ago