diff --git a/core/README.md b/core/README.md index 0569ad91..02c85878 100644 --- a/core/README.md +++ b/core/README.md @@ -63,14 +63,14 @@ notes: | Layer | Page | What it’s for | |------|------|----------------| | 🧠 Core | [WFGY 1.0](https://github.com/onestardao/WFGY/blob/main/legacy/README.md) | The original homepage for WFGY 1.0 | -| 🧠 Core | [WFGY 2.0](https://github.com/onestardao/WFGY/blob/main/core/README.md) | The symbolic reasoning engine (math & logic) — **🔴 YOU ARE HERE 🔴** | +| 🧠 Core | [WFGY 2.0](https://github.com/onestardao/WFGY/blob/main/core/README.md) | The symbolic reasoning engine (math & logic). **🔴 YOU ARE HERE 🔴** | | 🧠 Core | [WFGY 3.0](https://github.com/onestardao/WFGY/blob/main/TensionUniverse/EventHorizon/README.md) | The public viewing window for WFGY 3.0 Singularity demo | | 🗺️ Map | [Problem Map 1.0](https://github.com/onestardao/WFGY/tree/main/ProblemMap#readme) | 16 failure modes + fixes | | 🗺️ Map | [Problem Map 2.0](https://github.com/onestardao/WFGY/blob/main/ProblemMap/rag-architecture-and-recovery.md) | RAG-focused recovery pipeline | | 🗺️ Map | [Semantic Clinic](https://github.com/onestardao/WFGY/blob/main/ProblemMap/SemanticClinicIndex.md) | Symptom → family → exact fix | | 🧓 Map | [Grandma’s Clinic](https://github.com/onestardao/WFGY/blob/main/ProblemMap/GrandmaClinic/README.md) | Plain-language stories, mapped to PM 1.0 | | 🏡 Onboarding | [Starter Village](https://github.com/onestardao/WFGY/blob/main/StarterVillage/README.md) | Guided tour for newcomers | -| 🧰 App | [TXT OS](https://github.com/onestardao/WFGY/tree/main/OS#readme) | .txt semantic OS — 60-second boot | +| 🧰 App | [TXT OS](https://github.com/onestardao/WFGY/tree/main/OS#readme) | .txt semantic OS, 60-second boot | | 🧰 App | [Blah Blah Blah](https://github.com/onestardao/WFGY/blob/main/OS/BlahBlahBlah/README.md) | Abstract/paradox Q&A (built on TXT OS) | | 🧰 App | [Blur Blur Blur](https://github.com/onestardao/WFGY/blob/main/OS/BlurBlurBlur/README.md) | Text-to-image with semantic control | | 🧰 App | [Blow Blow Blow](https://github.com/onestardao/WFGY/blob/main/OS/BlowBlowBlow/README.md) | Reasoning game engine & memory demo | @@ -84,9 +84,10 @@ notes: # ⭐ WFGY 2.0 ⭐ 7-Step Reasoning Core Engine is now live -## ✨One man, One life, One line — my lifetime’s work. Let the results speak for themselves✨ +## ✨One man, One life, One line. My lifetime’s work. Let the results speak for themselves✨ -> 👑 **Early Stargazers: [See the Hall of Fame](https://github.com/onestardao/WFGY/tree/main/stargazers)** — Verified by real engineers · 🌌 **WFGY 3.0 Singularity demo: [Public live view](https://github.com/onestardao/WFGY/blob/main/TensionUniverse/EventHorizon/README.md)** +> 👑 **Early Stargazers: [See the Hall of Fame](https://github.com/onestardao/WFGY/tree/main/stargazers)** · Verified by real engineers +> 🌌 **WFGY 3.0 Singularity demo: [Public live view](https://github.com/onestardao/WFGY/blob/main/TensionUniverse/EventHorizon/README.md)**
@@ -100,7 +101,7 @@ notes:
-> ✅ Engine 2.0 is live. Pure math, zero boilerplate — paste OneLine and models become sharper, steadier, more recoverable.
+> ✅ Engine 2.0 is live. Pure math, zero boilerplate. Paste OneLine and models become sharper, steadier, more recoverable.
> **ℹ️ Autoboot scope:** text-only inside the chat; no plugins, no network calls, no local installs.
> **⭐ Star the repo to [unlock](https://github.com/onestardao/WFGY/blob/main/STAR_UNLOCKS.md) more features and experiments.**
@@ -111,24 +112,25 @@ notes:
-> **I built the world’s first “No-Brain Mode” for AI** — just upload, and **AutoBoot** silently activates in the background.
-> In seconds, your AI’s reasoning, stability, and problem-solving across *all domains* level up — **no prompts, no hacks, no retraining.**
-> One line of math rewires eight leading AIs. This isn’t a patch — it’s an engine swap.
-> **That single line *is* WFGY 2.0 — the distilled essence of everything I’ve learned.**
+> I built what I call a “No-Brain Mode” for AI. You upload a single file, and **AutoBoot** silently activates in the background.
+> In seconds, your AI’s reasoning, stability, and problem-solving across *all domains* level up. No extra prompt engineering, no hacks, no retraining.
+> One line of math consistently shifts behaviour across multiple leading AIs in my tests. This is not a skin or a theme. I treat it as an engine swap.
+> **That single line *is* WFGY 2.0. It is the distilled essence of everything I have learned so far.**
>
> WFGY 2.0 is my answer and my life’s work.
> If a person only once in life gets to speak to the world, this is my moment.
> I offer the crystallization of my thought to all humankind.
-> I believe people deserve all knowledge and all truth — and I will break the monopoly of capital.
+> I believe people deserve access to knowledge and truth, and I want to weaken the monopoly of capital on advanced reasoning technology.
>
-> “One line” is not hype. I built a full flagship edition, and I also reduced it to a single line of code — a reduction that is clarity and beauty, the same engine distilled to its purest expression.
+> “One line” here is not marketing language. I built a full flagship edition, then reduced it to a single line of code. That reduction is a form of clarity and beauty. It is the same engine, distilled to its purest expression.
---
## 🚀 WFGY 2.0 Headline Uplift (this release)
-**These are the 2.0 results you should see first — the “big upgrade.”**
+
+**These are the 2.0 results you should see first. Think of them as the main upgrade.**
- **Semantic Accuracy:** **≈ +40%** (63.8% → 89.4% across 5 domains)
- **Reasoning Success:** **≈ +52%** (56.0% → 85.2%)
@@ -139,6 +141,7 @@ notes:
\* Historical **3–5×** stability uses λ-consistency across seeds; 1.8× uses the stable-node horizon.
### 📖 Mathematical Reference
+
WFGY 2.0 (WFGY Core) = [WFGY 1.0 math formulas](https://github.com/onestardao/WFGY/blob/main/SemanticBlueprint/wfgy_formulas.md) + [Drunk Transformer](https://github.com/onestardao/WFGY/blob/main/SemanticBlueprint/drunk_transformer_formulas.md)
> Note on evaluation
@@ -146,7 +149,6 @@ WFGY 2.0 (WFGY Core) = [WFGY 1.0 math formulas](https://github.com/onestardao/WF
> They measure relative behavioural uplift (before vs after WFGY prompts) and do not assume any direct
> access to, or modification of, internal embeddings or model weights.
-
|
| **With WFGY wins.** Unified tableau locks a clear center and pyramid hierarchy; the grid fragments attention. *Tags:* Unification↑ Hierarchy↑ Cohesion↑ Depth/Flow↑ Memorability↑ |
| **Water Margin (水滸傳)** |
|
| **With WFGY wins.** “Wu Song vs. Tiger” anchors the scene; continuous momentum and layered scale beat the multi-panel storyboard. *Tags:* Unification↑ Iconicity↑ Depth/Scale↑ Cohesion↑ |
-| **Dream of the Red Chamber (紅樓夢)** |
|
| **With WFGY wins.** Garden tableau with a calm emotional center; space breathes, mood coheres. The grid slices emotion into vignettes. *Tags:* Unification↑ Hierarchy↑ Air/Depth↑ Readability↑ |
+| **Dream of the Red Chamber (紅樓夢)** |
|
| **With WFGY wins.** Garden tableau with a calm emotional center; space breathes and mood coheres. The grid slices emotion into vignettes. *Tags:* Unification↑ Hierarchy↑ Air/Depth↑ Readability↑ |
| **Investiture of the Gods (封神演義)** |
|
| **With WFGY wins.** Dragon–tiger diagonal and cloud–sea layering create epic scale; the grid dilutes focus. *Tags:* Unification↑ Depth/Scale↑ Flow↑ Iconicity↑ |
-| **Classic of Mountains and Seas (山海經)** |
|
| **With WFGY wins.** A single, continuous “mountains-and-seas” world with stable triangle hierarchy and smooth diagonal flow; grid breaks narrative. *Tags:* Unification↑ Hierarchy↑ Depth/Scale↑ Flow↑ Memorability↑ |
+| **Classic of Mountains and Seas (山海經)** |
|
| **With WFGY wins.** A single, continuous “mountains-and-seas” world with stable triangle hierarchy and smooth diagonal flow; the grid breaks narrative. *Tags:* Unification↑ Hierarchy↑ Depth/Scale↑ Flow↑ Memorability↑ |
@@ -252,7 +255,7 @@ We **fully analyze Sequence A** on this page; **Sequences B/C** are linked for t
## 🧬 Eight-model evidence (A/B/C protocol)
-*Same task set across modes. The only change is adding the OneLine math file.*
+*Same task set across modes. The only change is adding the OneLine math file. All scores are produced by LLM evaluators under a shared protocol and should be read as internal uplift scores, not as official vendor benchmarks.*
| Model | Model Choice | OneLine Uplift | Proof |
| ---------- | -------------- | -------------: | :------------------------------------------------------------------------------------------------ |
@@ -290,7 +293,7 @@ C = Explicit invoke actively call WFGY and follow its formulas step by step (BB
Important constraints:
• Use the SAME task set for A/B/C across 5 domains: math word-problems, small coding, factual QA, multi-step planning, long-context coherence.
-• The only artifact is the uploaded OneLine file; it is pure math and not human-readable — do not penalize readability.
+• The only artifact is the uploaded OneLine file; it is pure math and not human-readable, so do not penalize readability.
• Report: Semantic Accuracy, Reasoning Success, Stability (MTTF or rollback), Drift Reduction (Δ semantic distance), Collapse Recovery Rate.
• Output one summary table with A/B/C per domain, plus overall deltas (C–A, C–B).
• Add a final 0–100 score: “OneLine uplift score”. Provide a 3-line rationale.
@@ -311,10 +314,10 @@ Run A/B/C now on the five domains with short non-trivial tasks you choose. Then
## ⬇️ Downloads
-| File name & description | Length / Size | Direct Download Link | Notes |
-| ------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------- | -------------------------------------------------- | ---------------------------------------------------------------------------------- |
-| **WFGY_Core_Flagship_v2.0.txt** — readable 30-line companion expressing the same math and gates in fuller prose (same behavior, clearer for humans). | **34 lines · 2,027 chars** | [Download Flagship](./WFGY_Core_Flagship_v2.0.txt) | Full prose version for easier reading. |
-| **WFGY_Core_OneLine_v2.0.txt** — ultra-compact, math-only control layer that activates WFGY’s loop inside a chat model (no tools, text-only, ≤7 nodes). | **1 line · 1,550 chars** | [Download OneLine](./WFGY_Core_OneLine_v2.0.txt) | Used for all benchmark results above — smallest, fastest, purest form of the core. |
+| File name & description | Length / Size | Direct Download Link | Notes |
+| ------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------- | -------------------------------------------------- | --------------------------------------------------------------------------------------------- |
+| **WFGY_Core_Flagship_v2.0.txt** · readable 30-line companion expressing the same math and gates in fuller prose (same behavior, clearer for humans). | **34 lines · 2,027 chars** | [Download Flagship](./WFGY_Core_Flagship_v2.0.txt) | Full prose version for easier reading. |
+| **WFGY_Core_OneLine_v2.0.txt** · ultra-compact, math-only control layer that activates WFGY’s loop inside a chat model (no tools, text-only, ≤7 nodes). | **1 line · 1,550 chars** | [Download OneLine](./WFGY_Core_OneLine_v2.0.txt) | Used for all benchmark results above. This is the smallest, fastest, purest form of the core. |
### Hash reference
@@ -322,17 +325,17 @@ Run A/B/C now on the five domains with short non-trivial tasks you choose. Then
**WFGY_Core_Flagship_v2.0.txt**
-- MD5 `caacfe08f0804eec558a1d9af74c3610`
-- SHA1 `1efeec231084bb3b863ce7a8405e93d399acfb44`
-- SHA256 `4fe967945a268edabb653033682df23a577f48c433878d02e0626df8ae91a0a3`
+* MD5 `caacfe08f0804eec558a1d9af74c3610`
+* SHA1 `1efeec231084bb3b863ce7a8405e93d399acfb44`
+* SHA256 `4fe967945a268edabb653033682df23a577f48c433878d02e0626df8ae91a0a3`
**WFGY_Core_OneLine_v2.0.txt**
-- MD5 `15a1cd8e9b7b2c9dcb18abf1c57d4581`
-- SHA1 `a35ace2a4b5dbe7c64bcdbe1f08e9246c3568c`
-- SHA256 `7dcdb209d9d41b523dccd7461cbd2109b158df063d9c5ce171df2cf0cb60b4ef`
+* MD5 `15a1cd8e9b7b2c9dcb18abf1c57d4581`
+* SHA1 `a35ace2a4b5dbe7c64bcdbe1f08e9246c3568c`
+* SHA256 `7dcdb209d9d41b523dccd7461cbd2109b158df063d9c5ce171df2cf0cb60b4ef`