Skip to content

feat: remove false Anthropic guardrails, add How It Works page#10

Merged
shrimpy8 merged 1 commit intomainfrom
feat/round-18-remove-anthropic-guardrails
Jan 31, 2026
Merged

feat: remove false Anthropic guardrails, add How It Works page#10
shrimpy8 merged 1 commit intomainfrom
feat/round-18-remove-anthropic-guardrails

Conversation

@shrimpy8
Copy link
Owner

Summary

  • Remove unnecessary Anthropic guardrails (XML exclusion block, temperature 0.1, Rule 6 EXCLUDED TOPICS) after manual verification confirmed all "suspicious" content was actually in the transcript
  • Add interactive How It Works architecture overview page with links from UI and docs
  • Create docs/SETUP.md, docs/API.md, docs/INFRASTRUCTURE.md; update README.md and prompts/README.md for accuracy
  • Full 9-combination test (3 providers x 3 styles) passed with 0 hallucinations — Anthropic is now chore(deps): Bump vitest from 4.0.14 to 4.0.15 #1 across all modes

Test plan

  • npx tsc --noEmit — pre-existing test file errors only, no new errors
  • npm test -- --run — 339/339 tests pass
  • Manual UI test: all 9 LLM combinations generated successfully
  • TXT exports verified for all 9 combinations
  • Zero hallucinations across all outputs
  • Analysis report created at ai_summary/ANALYSIS_REPORT.md

🤖 Generated with Claude Code

…e docs

Round 18 prompt tuning: after manual verification confirmed that all
"suspicious" Anthropic output (interview prep, business metrics, career
advice) was actually present in the transcript, removed the unnecessary
guardrails that were suppressing legitimate content.

Changes:
- Delete prompts/anthropic-exclusions.xml (XML exclusion block)
- Remove exclusion loading code from llm-api-helpers.ts
- Raise Anthropic temperature from 0.1 to 0.7
- Remove Rule 6 "EXCLUDED TOPICS" from all 3 prompt templates
- Add interactive How It Works page (public/how-it-works.html)
- Add How It Works links to UrlInput, Footer, and all docs
- Create docs/SETUP.md, docs/API.md, docs/INFRASTRUCTURE.md
- Update README.md and prompts/README.md for accuracy
- Add Round 18 test results (9/9 pass, 0 hallucinations)
- Add ai_summary/ANALYSIS_REPORT.md with full quality analysis

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
@shrimpy8 shrimpy8 merged commit b04224e into main Jan 31, 2026
@shrimpy8 shrimpy8 deleted the feat/round-18-remove-anthropic-guardrails branch February 2, 2026 02:25
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant