docs: rewrite hero around general-purpose positioning - #24
Merged
Conversation
The previous hero opened with a specific worked example (Qwen3.6 + SWE-bench Verified + GPT-5.5). That framing reads as "this tool exists to optimize Qwen3.6 against SWE-bench", which buries the actual product: a *general-purpose evolution runtime* that works against any git repository and any measurable goal. This pass reframes the hero around what the runtime is, with the SWE-bench example demoted into a clearly-labeled worked example further down the page. Specific changes: - Hero headline: "Take a 3 B-active open-weight model..." → "A soul plugin for any code." - New second-paragraph framing: the codebase, once given a goal, begins to perceive its environment, judge its output, and rewrite itself toward the goal — sandboxed, ledgered, reversible. - New short evocative paragraph below describing the conceptual shift: code-as-text becomes code-as-process when it can read its own outputs and shed failed experiments without scarring. - Section heading "## Our v1.1 target" → "## A worked example: SWE-bench Verified (our v1.1 target)". Same content; the heading now signals that the example is *one* demonstration of the runtime, not the runtime's purpose. English (README.md) and Chinese (README.zh.md) hero blocks rewritten in lock-step. No code changes; the rest of the README (motivation, what-it-does, architecture, configuration, etc.) is untouched. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
There was a problem hiding this comment.
Pull request overview
Documentation-only PR that reframes the README hero from a specific SWE-bench/GPT-5.5 comparison to a general-purpose positioning ("a soul plugin for any code"), and relabels the SWE-bench section as a worked example. Changes are mirrored across English and Chinese READMEs.
Changes:
- Rewrite hero copy in
README.mdto emphasize general-purpose runtime positioning - Mirror the same rewrite in
README.zh.mdto keep both languages in lock-step - Rename the SWE-bench section heading to clarify it is one example, not the runtime's purpose
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| README.md | Hero rewritten to general-purpose framing; SWE-bench section heading clarified as a worked example |
| README.zh.md | Same hero rewrite and heading clarification in Chinese, kept in sync with the English version |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
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.
Summary
Previous hero opened with the SWE-bench / Qwen3.6 / GPT-5.5 example. That framing buries the actual product: a general-purpose evolution runtime that works against any git repository and any measurable goal. Readers were left to infer the generality from later sections.
This pass reframes the hero around what the runtime is, with the SWE-bench example clearly demoted into a worked example further down.
Changes
Hero (both languages, lock-stepped):
Before — "Take a 3 B-active open-weight model. Close most of the SWE-bench gap to GPT-5.5..."
After — "A soul plugin for any code." + a paragraph describing what happens when you drop it into any repo (perceive, judge, rewrite toward the goal — sandboxed, ledgered, reversible) + a short evocative paragraph framing the conceptual shift (code-as-text becomes code-as-process).
Section heading:
## Our v1.1 target→## A worked example: SWE-bench Verified (our v1.1 target)Same content; the heading now signals the example is one demonstration of the runtime, not the runtime's purpose.
Test plan
README.mdandREADME.zh.mdrewritten in lock-step.🤖 Generated with Claude Code