docs(readme): soften absolute claims and de-recycle benchmark headline - #451
Merged
Conversation
Align the public landing page with the corrected launch messaging so a hostile first-click reader cannot quote an overclaim back at us: - Replace the absolute tagline and the "secrets never reach the provider" heading with bounded, guardrail-accurate wording. - Add a "Known limitations" section (DLP is a guardrail not a boundary, spend caps are per-call, compliance is not certification, young project). - Reframe the benchmark headline (README + benchmarks.md): lead with the measured ~90 us full-stack-with-DLP overhead instead of the recycled "40x faster than LiteLLM" line, and contextualize bare-proxy numbers. - Offer an IPv4 fallback in the quickstart health check. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Hardens the public README + benchmark doc ahead of launch, based on three independent launch premortems (GPT-5, Codex, Claude). Wording/positioning only — no behavior change, no claim beyond what the code does.
benchmarks.md): replace the recycled "40x faster than LiteLLM" line (it is a competitor's blog title, and the table itself shows a bare proxy posting lower raw numbers) with the honest owned claim — ~90 µs full-stack-with-DLP overhead, sub-ms vs LiteLLM, bare proxies faster only by running none of these features.127.0.0.1fallback for IPv4-only setups.Why
A hostile first-click reader could otherwise quote an overclaim back at us. Every line now matches the codebase and the careful framing of the launch post.
🤖 Generated with Claude Code