docs: rework README tone — sound like dev docs, not a pitch deck - #23
Merged
Conversation
The previous rewrite framed the value proposition explicitly: a
section literally titled "The 30-second pitch" with an
emoji-decorated table of Economics / Engineering / Strategy. That
reads as marketing copy in a developer-community README. Same
substance, but the form telegraphs the audience and dilutes
credibility with peer developers.
This pass keeps the content (cost / reliability / portability) but
moves it into the kind of section developer READMEs actually have:
- "The 30-second pitch" → "Motivation" — standard dev-doc heading
- 3-row emoji table → 3 plain bullets framed in engineering terms:
* "Inference cost collapses" (the dollars-vs-cents reality)
* "Production reliability is mechanical, not aspirational"
(ledger / sandbox / line-count anchor)
* "A harness is a portable asset" (transfer + compounding)
- Removed "multi-billion-dollar dynamic", "shipping agent products",
"bespoke labor done by senior staff", "reproducible / transferable
/ compoundable" — all phrasings that read as investor-deck syntax
rather than engineering observation.
Also de-marketed two other lines in the Roadmap target section:
- "**The thesis.**" → "**Why this gap is closable.**"
- "**What this story will demonstrate when it lands.**" →
"**Why this run is worth doing.**"
The "story" framing implied a script being executed. The new framing
asks the engineering question the run is meant to answer.
English and Chinese READMEs updated in lock-step. No code changes.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
There was a problem hiding this comment.
Pull request overview
This PR updates the English and Chinese READMEs to adopt a more developer-docs tone by replacing pitch/deck-style sections with standard engineering-motivation framing, while preserving the underlying value propositions (cost, reliability, portability).
Changes:
- Rename the pitch-style section to a developer-oriented “Motivation/动机” section.
- Replace the emoji/value table with plain engineering bullets describing cost, reliability, and portability.
- Rephrase two roadmap callouts to be less “deck-like” (“The thesis/story…” → “Why this gap is closable / Why this run is worth doing”, and the Chinese equivalents).
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.
| File | Description |
|---|---|
| README.md | Reworks the early “pitch” section into a “Motivation” section with engineering-style bullets and rephrased roadmap callouts. |
| README.zh.md | Mirrors the README.md tone/structure changes in Chinese, including the roadmap callout rephrases. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| What that buys you, concretely: | ||
|
|
||
| - **Inference cost collapses.** A 3 B-active model runs locally at fractions of a cent per task; the frontier APIs (GPT-5.5, Claude Opus 4.7) bill in dollars. Closing the capability gap *without retraining* moves an agent stack from "expensive to run at scale" to "near-zero marginal cost at scale". | ||
| - **Production reliability is mechanical, not aspirational.** Every decision is ledgered, every accepted change is a named git commit, every experiment runs in a git-worktree sandbox plus a firejail OS-level sandbox. The whole runtime is ~1,900 lines and was designed to be put in production, not demoed. |
Comment on lines
100
to
+102
| **Why this model.** [Qwen3.6-35B-A3B](https://qwen.ai/blog?id=qwen3.6-35b-a3b) is Alibaba's flagship open-weight model (Apache 2.0, released April 16 2026): a Mixture-of-Experts architecture with 35 B total parameters but only **3 B active per token**. It runs on a single consumer GPU. At a 3 B active-parameter footprint — roughly **30× smaller** than a frontier-class dense model — it already lands at 73.4 % on SWE-bench Verified, **within 15 points of GPT-5.5 while costing fractions of a cent per task to run locally**. | ||
|
|
||
| **The thesis.** That 73.4 % is the result of months of hand-tuned harness engineering by the Qwen team. Closing the remaining gap to GPT-5.5 (88.7 %) is exactly the kind of work Evolution Kernel automates — the planner converges on better tool selection, parallel sampling, verifier loops, and error-pattern recovery. Same model, same weights, evolved harness. | ||
| **Why this gap is closable.** That 73.4 % already represents months of hand-tuned harness engineering by the Qwen team. The remaining gap to GPT-5.5 (88.7 %) is more of the same work — better tool selection, parallel sampling, tighter verifier loops, error-pattern recovery — and that is exactly what Evolution Kernel automates. Same model, same weights, an evolved harness. |
| **为什么选这个模型。** [Qwen3.6-35B-A3B](https://qwen.ai/blog?id=qwen3.6-35b-a3b) 是阿里 2026-04-16 发布的开源旗舰（Apache 2.0）：35 B 总参 Mixture-of-Experts 架构，**每 token 只激活 3 B**。一张消费级 GPU 就能跑。3 B 激活参数足迹——比旗舰稠密模型**小约 30 倍**——在 SWE-bench Verified 上已经做到 73.4%，**距离 GPT-5.5 只差 15 分，而本地推理成本是每任务几分钱**。 | ||
|
|
||
| **核心论点。** 那 73.4% 是 Qwen 团队几个月人肉调 harness 的成果。把剩下到 GPT-5.5（88.7%）的差距闭合，恰好是 Evolution Kernel 自动化的工作——规划器会收敛到更好的工具选择、并行采样、验证器循环、错误模式恢复。同一个模型，同一份权重，进化后的 harness。 | ||
| **为什么这个差距可以闭合。** 那 73.4 % 本身已经是 Qwen 团队几个月人肉 harness 工程的产物。剩下到 GPT-5.5（88.7 %）的差距，是同类型的工程工作——更好的工具选择、并行采样、更紧的验证器循环、错误模式恢复——而这正是 Evolution Kernel 自动化掉的事。同一个模型，同一份权重，一份进化过的 harness。 |
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
The prior README rewrite framed the value proposition explicitly: a section titled "The 30-second pitch" with an emoji table of Economics / Engineering / Strategy. The substance was right, but the form telegraphs that the README is written for investors — which undercuts credibility with the peer developers it sits in front of.
This pass keeps the content (cost / reliability / portability) but moves it into the kind of section developer READMEs actually have. An investor who reads dev docs the way developers do will still land on the same takeaways; they just won't feel handled.
What changed
## The 30-second pitch→## Motivation— standard dev-doc heading.English and Chinese READMEs updated in lock-step. No code changes.
Test plan
grep -niE "pitch|elevator|moat|strategic|story will|thesis|演讲|核心论点|落地后将"→ no remaining matches in README copy (the onlyhistorymatches are the existinghistory injectionfeature name).🤖 Generated with Claude Code