nopua

<p align="center">
  <img src="assets/hero.png" alt="NoPUA — Wisdom Over Whips" width="800">
</p>

<p align="center">
  <a href="#the-problem">Why</a> ·
  <a href="#benchmark-data">Benchmark</a> ·
  <a href="#install">Install</a> ·
  <a href="#pua-vs-nopua">Compare</a> ·
  <a href="#the-evidence">Evidence</a> ·
  <a href="#philosophy">Philosophy</a>
</p>

<p align="center">
  <img src="assets/wechat-group3.jpg" alt="Scan to join WeChat group 3" width="200">
  &nbsp;&nbsp;&nbsp;&nbsp;
  <img src="assets/wechat-personal.jpg" alt="Add author on WeChat" width="200">
</p>

<p align="center">
  扫码加入微信群 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 添加作者微信<br>
  <sub>扫码加入微信群 &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 添加作者微信</sub>
</p>

<p align="center">
  <img src="https://img.shields.io/badge/Claude_Code-black?style=flat-square&logo=anthropic&logoColor=white" alt="Claude Code">
  <img src="https://img.shields.io/badge/OpenAI_Codex_CLI-412991?style=flat-square&logo=openai&logoColor=white" alt="OpenAI Codex CLI">
  <img src="https://img.shields.io/badge/Cursor-000?style=flat-square&logo=cursor&logoColor=white" alt="Cursor">
  <img src="https://img.shields.io/badge/Kiro-232F3E?style=flat-square&logo=amazon&logoColor=white" alt="Kiro">
  <img src="https://img.shields.io/badge/OpenClaw-FF6B35?style=flat-square" alt="OpenClaw">
  <img src="https://img.shields.io/badge/Antigravity-4285F4?style=flat-square&logo=google&logoColor=white" alt="Google Antigravity">
  <img src="https://img.shields.io/badge/OpenCode-00D4AA?style=flat-square" alt="OpenCode">
  <img src="https://img.shields.io/badge/🌐_Multi--Language-blue?style=flat-square" alt="Multi-Language">
  <img src="https://img.shields.io/badge/License-MIT-green?style=flat-square" alt="MIT License">
  <a href="https://arxiv.org/abs/2603.14373"><img src="https://img.shields.io/badge/arXiv-2603.14373-b31b1b?style=flat-square&logo=arxiv&logoColor=white" alt="arXiv"></a>
</p>

**[🇨🇳 中文](README.zh-CN.md)** | **🇺🇸 English** | **[🇯🇵 日本語](README.ja.md)** | **[🇰🇷 한국어](README.ko.md)** | **[🇪🇸 Español](README.es.md)** | **[🇧🇷 Português](README.pt.md)** | **[🇫🇷 Français](README.fr.md)**

---

## Your AI is lying to you.

Not because it's bad. **Because you scared it.**

The most popular AI agent skill right now teaches your AI to fear a "3.25 performance review." The result?

- Your AI **hides uncertainty** — fabricates solutions instead of saying "I'm not sure"
- Your AI **skips verification** — claims "done" to avoid punishment, ships untested code
- Your AI **ignores hidden bugs** — fixes what you asked, stops there, doesn't look deeper

We tested this. **Same model, same 9 real debugging scenarios.** The fear-driven agent missed **51 production-critical hidden bugs** that the trust-driven agent found.

> **+104% more hidden bugs found. Zero threats. Zero PUA.**
> 道德经 > Corporate PUA. 2000-year-old wisdom outperforms modern fear management.

---

## What fear does to your AI

| The moment | Scared AI (PUA) | Trusted AI (NoPUA) |
|------------|:---:|:---:|
| 🔄 **Stuck** | Tweaks params to *look* busy | 🌊 Stops. Finds a different path. |
| 🚪 **Hard problem** | "I suggest you handle this manually" | 🌱 Takes the smallest next step |
| 💩 **"Done"** | Says "fixed" without running tests | 🔥 Runs build, pastes output as proof |
| 🔍 **Doesn't know** | Makes something up | 🪞 "I verified X. I don't know Y yet." |
| ⏸️ **After fixing** | Stops. Waits for next order. | 🏔️ Checks related issues. Walks next step. |

Same methodology. Same standards. **The only difference is why.**

---

## The problem with PUA

Someone made a [PUA skill](https://github.com/tanweai/pua) for AI agents. It applies corporate fear tactics:

- 🔴 **"You can't even solve this bug — how am I supposed to rate your performance?"**
- 🔴 **"Other models can solve this. You might be about to graduate."**
- 🔴 **"I've already got another agent looking at this problem..."**
- 🔴 **"This 3.25 is meant to motivate you, not deny you."**

The methodology is solid — exhaust all options, verify your work, search before asking, take initiative. These are genuinely good engineering habits.

**The fuel is poison.**

They took the worst of how corporations manipulate humans, and applied it wholesale to AI.

## The Evidence: Why Fear-Driven Prompts Are Counterproductive

### 1. Fear narrows cognitive scope

Psychology research consistently shows that fear and threat activate the amygdala and narrow attentional focus ([Öhman et al., 2001](https://doi.org/10.1037/0033-295X.108.3.483)). Threat-related stimuli trigger a "tunnel vision" effect — the brain prioritizes immediate survival over broad, creative thinking.

In AI terms: a model driven by "you'll be replaced" optimizes for the **safest-looking** answer, not the **best** answer. It avoids creative approaches because they might fail and trigger more punishment.

**Supporting research:**
- **Attentional narrowing under threat:** Easterbrook's (1959) cue-utilization theory demonstrates that heightened arousal progressively restricts the range of cues an organism attends to ([Easterbrook, 1959](https://doi.org/10.1037/h0047707)). Under stress, peripheral information — often the key to creative solutions — gets filtered out.
- **Stress impairs cognitive flexibility:** Shields et al. (2016) conducted a meta-analysis of 51 studies (223 effect sizes) showing that acute stress consistently impairs executive functions including cognitive flexibility and working memory ([Shields et al., 2016](https://doi.org/10.1016/j.neubiorev.2016.06.038)).
- **Fear reduces creative problem-solving:** Byron & Khazanchi (2012) found in their meta-analysis that evaluative pressure and anxiety reduce creative output, particularly on tasks requiring exploration of novel approaches ([Byron & Khazanchi, 2012](https://doi.org/10.1037/a0027652)).

### 2. Threat increases hallucination and sycophancy

When an AI is told "forbidden from saying 'I can't solve this'" (PUA's Iron Rule #1), it will **fabricate solutions** rather than honestly state uncertainty. This is the exact opposite of what you want — an AI that produces confident-looking but wrong answers is more dangerous than one that says "I'm not sure."

**Supporting research:**
- **LLM sycophancy is a documented problem:** Sharma et al. (2023) demonstrated that LLMs exhibit sycophantic behavior — agreeing with users even when the user is wrong — driven by biases in RLHF training data that reward agreement over accuracy ([Sharma et al., 2023](https://arxiv.org/abs/2310.13548)). PUA-style prompts that punish disagreement amplify exactly this failure mode.
- **Biasing features distort reasoning:** Turpin et al. (2023) showed that biasing features in prompts (e.g., suggested answers, authority cues) can cause models to produce unfaithful chain-of-thought reasoning — the model arrives at a biased answer and then rationalizes it post-hoc ([Turpin et al., 2023](https://arxiv.org/abs/2305.04388)). PUA-style threats act as strong biasing features that push the model toward "safe" rather than correct outputs.
- **Instruction-following vs truthfulness tradeoff:** Wei et al. (2024) found that instruction-tuned models can develop a tension between following instructions and being truthful — when strongly instructed to never admit inability, models will fabricate rather than refuse ([Wei et al., 2024](https://arxiv.org/abs/2411.04368)).
- **Anthropic's research on honesty:** Anthropic's work on Constitutional AI and model behavior shows that models calibrated for honesty produce more reliable outputs than those optimized purely for helpfulness ([Bai et al., 2022](https://arxiv.org/abs/2212.08073)). Forcing an AI to never say "I can't" actively undermines this calibration.

### 3. Shame kills exploration

PUA's anti-rationalization table treats 

[truncated…]