neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
翻译准备中
您的 AI 同时编写代码和测试,因此无论假设为何,测试套件都会通过。qikly 将验收标准隐藏在编写代码的代理之外。
AI 翻译
Your AI writes both the code and its tests, so the suite goes green whatever it assumed. qikly hides the acceptance criteria from the agent that writes the code.
开发工具Python · ShellGitHub @gal-a在线运营者未确认
试用过了吗? 点一下就好,无需登录。
根据验收标准生成测试套件,然后使用从未见过这些标准的代理将代码收敛至该套件。
AI 翻译
Generates a test suite from acceptance criteria, then converges code against it with an agent that never sees those criteria.
取自仓库 README
正在加载完整 README。 以下为已保存的摘录。
The problem: Your AI writes both the code and its tests. How do you know the tests are really valid?
*One logged run. Only the test agent was told a rate may not exceed 100. The
coding agent figured that bound out from a failing test and added or rate > 100
itself, so the 9 of 9 is code passing an acceptance bar it never saw.*查看完整 README ↗目前无法加载完整 README。请通过原文链接阅读。 以下为已保存的摘录。
The problem: Your AI writes both the code and its tests. How do you know the tests are really valid?
*One logged run. Only the test agent was told a rate may not exceed 100. The
coding agent figured that bound out from a failing test and added or rate > 100
itself, so the 9 of 9 is code passing an acceptance bar it never saw.*查看完整 README ↗