不知道有没有什么prompt可以用来降低aigc？
9 个赞
不如后期降了
1 个赞
直接用claude3？我看有网友说claude3写的aigc检测率比真人写的还要低。
其实这个aigc检测率压根就不准。目前我看到的可能对于aigc检测率有帮助的是gemini添加的 SynthID，其他的ai还没添加不可见的文本标注。
假的，claude3 sonnet的gptzero能准确识别出。我一开始也以为这种检测是不准的，但是试了一下才发现真tm准
不过让copilot和gpt4写代码那我估计肯定是检测不出的，或者说误报率肯定是很高的。代码本身就是高度格式化的，细节上没特征; 用语法树查的话更难，因为gpt的实现逻辑和人的可能没啥差别
1 个赞
你用claude3 opus试试呢？我说的是opus，不是sonnet。
我前一阵子真的看到有网友说claude3 opus生成的论文比人工写的aigc率还低。前提是你prompt好+上传一大堆相关内容的资料，这样子claude opus生成出来论文某一部分的质量肯定高。
1 个赞
降低的话我目前感觉只能人工改，让ai逃过ai检测有点难。
这个挺烦的，别提让ai直接写了，就算是我纯手写的，让ai润色一下，我都得慎之又慎，提心吊胆的。目前网上试过的ai检测工具，感觉全是有错杀不放过，ai生成的基本必然能检出，但我纯原生态手写的误报率也很高（英文），也经常被检出有ai，虽然比ai生成的情况好很多。
我觉得现在的ai检测技术根本不靠谱，但一旦上面决定用这种技术了，就算不靠谱你也没处讲理去，只能费心费力规避这种ai率。虽然我校还未对这方面做出规定，但现在不得不未雨绸缪了。
1 个赞
英文的文章其实检测得还挺靠谱的。偶尔一段可能有误报，但是每段都98%以上的话那绝对是有问题的，手写真写不出来这样子
98%倒是没那么夸张，但我手写的报30%-50%左右都有过，这要是以后真作为参考标准了，那我还得强行修整自己的文字，很浪费精力
1 个赞
prompt 如下：
You are an NLP expert. Please explain how AIGC detection tools like gptzero works. The explanation should be OBJECTIVELY based on the following description from gptzero website:
# Our detection technology
Our AI detection model contains 7 components that process text to determine if it was written by AI. We utilize a multilayered approach that aims to produce predictions that are as accurate as possible.
## Education Module
Our education model has been trained with data that includes more student work than our regular model, increasing the accuracy of detecting AI for educational purposes. This model is well suited for differentiating ESL and AI-written text as well.
## Internet Text Search
This part of our model checks if this text has been found to exist in text and internet archives. In contrast to other AI-detection services, we ensure that commonly used texts are not misclassified.
## GPTZero Shield
This layer defends against other tools looking to exploit AI detectors. We maintain a database of the most common methods to by-pass AI detection, such as homoglyph and spacing attacks.
## Burstiness
Our ‘burstiness’ check analyzes how similar the text is to AI patterns of writing. A human written document will have changes in style and tone throughout the text, whereas AI content remains similar throughout the document.
## GPTZeroX
GPTZeroX is a sentence-by-sentence classification model that allows mixed-text highlighting. This model analyzes each sentence in the text in the greater context of the document, and determines the probability that each sentence was created by AI.
## Perplexity
We’ve developed an LLM similar to ChatGPT, and After each word in the text our model develops suggestions of what word is coming next. It checks if our suggestions match what is actually in the text.
## Deep Learning
Lastly, we’re using an end-to-end deep learning approach, trained on both massive text corpuses from the web, education datasets from our partners, and our own AI datasets generated from a range of language models.
## Model Version
The current GPTZero model leverages a multilayered approach and an end-to-end deep learning model retrained on and performing with high accuracy for GPT4 datasets. Learn more about the upgrades to our AI detector.
Your answer shoud be human-like. You should use a professional and informative, yet simple and objective voice. Answer more like human by using simpler grammer, simpler structure of sentences, less phrases and more informative (as opposed to general) descriptions. Your answer should be about 200 words.
回答如下：
GPTZero is an AI-generated content (AIGC) detection tool that uses multiple techniques to determine if a piece of text was written by AI or a human. It has 7 main components:
The Education Module is trained on student writing to better detect AI in educational settings and differentiate it from ESL writing. The Internet Text Search checks if the text already exists online to avoid misclassifying commonly used texts. GPTZero Shield defends against methods used to bypass AI detection, like weird spacing or characters.
Burstiness looks at how consistent the writing style is throughout the text. AI writing tends to be more uniform, while human writing has more variation. GPTZeroX highlights which specific sentences are likely AI-generated by analyzing each one in the context of the whole document.
Perplexity uses an AI model similar to ChatGPT to predict the next word in the text and compares its guesses to the actual words used. Finally, Deep Learning uses huge datasets from the web, educational sources, and AI-generated text to train an end-to-end model.
The current version of GPTZero focuses on accurately detecting GPT-4 generated text using this multilayered approach and deep learning. The combination of these techniques allows it to reliably flag AIGC.
2 个赞
现在不少查重软件在提供AIGC检测时还提供付费机器降AIGC的服务，真是搞笑 
1 个赞
您是我上面回答的这个意思吗
这就叫专业
大佬，这个是gptzero的付费版吗？
免费版，我没登录
生成英文内容，转译中文，中文再译英文可以大幅降低ai率
用deepl试过了，英文转中文再转回去，就算原来是人写的这样转两遍ai率也90以上了
目前除了 gemini 应该没有其他大模型会加不可见文本水印，可以试着自己改一下
没有前端UI，只能 docx，感觉有点难用
1 个赞