可以用提示语“找出 swear 率低于平均水平的文件”来对源代码运行 AI 吗？
1 分•作者: pcwir•大约 2 个月前
因为“脏话多的代码质量更高”，这意味着很多人都看过这段代码，而且看这段代码的人越多，平均来说就越有可能找到脏话。<p>如果这是真的，为什么不通过在开源代码上运行人工智能并给出“找到低于平均脏话率的文件”的提示来进行测试呢？（为了节省token，这个提示被缩短了。）<p>此外，有人可以编写一个程序，添加补丁，以人类打字的概率将随机脏话分发到开源代码中。<p>只是问问是否有人想运行这个，因为我负担不起运行昂贵的人工智能，或者将这些随机的脏话注释添加到所有开源代码项目中，然后等待，因为很多人可能会拒绝我的补丁。如果有人愿意，我希望其他人来做这件事，因为如果你想做，那就太好了。<p>是的，这是一种“通过模糊性实现安全”的方法，但这可能会阻止人工智能提交关于“这段代码有漏洞”的问题，而实际上它并没有（参见curl作者对人工智能生成问题的回应），因为它会想：“嗯，脏话数量平均，一定是好代码，总之，让我去别的地方看看。”
查看原文
Because “code with more swear words is higher quality”, meaning lots of humans looked at that code and the more humans look at that code, the more swear words could be found on average.<p>If this is true, then why not put it to the test by running an A.I. on open source code and giving it the prompt of “Find below-avg swear rate files” (This prompt was shortened to save on tokens.)<p>Also, someone could make a program add patches that would distribute random swear words into open source code with the probability of a human typing it in.<p>Just asking whether someone wants to run this, because I can’t afford to run expensive A.I. or add these randomized swear word comments to all open source code projects and then wait as many might refuse my patches. I’d like for someone else to do this if they want to, because if you want to, then cool.<p>Yes, this is “security through obscurity”, but this might discourage AIs from submitting issues about how “this code is vulnerable” when it’s not (see curl author’s response to AI created issues) because it’ll go: “Hmm, average amount of swear words, must be good code, anyway, let me look somewhere else.”