Rate My New Content AI

How did you test that?

That was the same "plagiarism test" I did. I'm looking into tools now, but so far so good. Well to train a model you need data so why not both?



Plagiarism Update:
So I ran the text through Quetext and the results seem promising. They indicated 13% was "plagiarized", but when you look into the details its very weak evidence and not real plagiarism IMO. I'd love some feedback on this "plagiarism" and whether Google would penalize this content.

View attachment 195314
View attachment 195315
View attachment 195316
i used https://searchenginereports.net/plagiarism-checker
but as you said its looks very weak evidence from a google search
 
I just do a quick check on smallseotools.com/plagiarism-checker. This is what I got. But your AI is top notch as compare to other tools I use. Just keep tweaking.
TxCSqGrUP8.png
 
I'm not sure what route I'm going to take. I'm gonna just keep testing and improving it for now.

Why not allow a select few of BHW members to test it? That way we can give you a better feedback on the tool.
 
Great results! Congrats, I would be one of your first customers.
 
I’m still tweaking the overall program/process and this was the very first test.


Any recommendations for plagiarism checkers? I’ve tried googling random portions of the text and can’t find any explicit plagiarism.
Quetext is much better than Copyscape.
 
This looks promising. I'm running a content business and I use a few AI tools to write and they all need a hell of manual editing.
Your content looks good. I'd love to be a beta tester when you put this out for public.
 
Hello everyone,
For the past few weeks I've been working on a specific AI use case and I'm finally beginning to see results.
I'd like to see what others here think of the quality of the content and more importantly how it compares to other AI services on the market. (Jarvis, GPT3, etc)

The content is 100% AI created with my only input being the title of the page (I don't even include a structure) and once in a while deleting certain paragraphs. For this example, I'm using the water/fire damage restoration niche.

Example 1 - https://pastebin.com/BJFTyRj3
Example 2 - https://pastebin.com/3EAyhSr6

That's impressive, I thought content creation AI was developed by large teams only. How do you even go about developing such an AI? Must have taken you some time to do on your own.
 
Did you check the grammar and plagiarism. Article Great well written. thank you keep it up
 
That's impressive, I thought content creation AI was developed by large teams only. How do you even go about developing such an AI? Must have taken you some time to do on your own.
Just look into pre existing AI’s and expanding their capabilities :)
 
I'm really starting to wonder if these AI writers are just front for a bunch of rock bottom low paid people in 3rd world countries who do a quick Google search and paraphrase the article live in front of you at 300wpm.
 
The major problem with all the AI writers is the facts. Since I don't know anything about home construction or roofing, how am I supposed to know as a reader that the information/tips/suggestions mentioned in the article are valid and effective unless a person specializing in home construction has written it. it is difficult for me as a writer also, since I also don't know anything about this niche. So I cannot even fact check it myself. Some users in other forums have said that I should know all the things in my niche since I should research....but I think, even if I research on the internet for that niche, I will not add something new to the article. It will just be a collection of old articles in a summarized form. I think new ideas/tips/suggestions can only be given by a person who has experience and has worked in that particular area. Now the question is that can AI get that sort of experience by absorbing/training all the information on the internet, even information that is unstructured (video, text, images)....I suppose it is possible since there are algos that can be trained on unstructured data....but the hardware needed will be at a quantum level that is yet to come. Also the question remains is that how can I fact check an article if I myself don't know if the methods/ideas mentioned in the article are true or not. @RoyDanino also pointed out that some info is incorrect but it looks to me that all info is correct. These are the problems that AI needs to resolve otherwise the search engines will fill up with regurgitated content by users like me who are subscribed to one of the GPT3 SAAS services. I am using these services to fill up the content on my site but I don't know if the info is correct or not and I hope big G also does not know! ;)

I would love the idea, if someone comes up with an AI service here to just fact check the articles.
Agreed. I've tested almost everything on the market and although some give better output than others, most of them fall short on "facts". Additionally, it's my understanding most crawled the web in 2019 so current events, updates, methodologies, etc, don't organically register. For me, this doesn't work because my niche is constantly changing and technical so I need up-to-date facts. I started testing outranking.io, and they've got a pretty good system that checks the boxes the others miss because they rely on SERP data from the top 20 current results. However, my 3-fold problem with them is their process is cumbersome, they're a little pricey in comparison and their templates are limited and focused primarily on long-form content type outputs. So far this has been an uber frustrating journey.
 
Agreed. I've tested almost everything on the market and although some give better output than others, most of them fall short on "facts". Additionally, it's my understanding most crawled the web in 2019 so current events, updates, methodologies, etc, don't organically register. For me, this doesn't work because my niche is constantly changing and technical so I need up-to-date facts. I started testing outranking.io, and they've got a pretty good system that checks the boxes the others miss because they rely on SERP data from the top 20 current results. However, my 3-fold problem with them is their process is cumbersome, they're a little pricey in comparison and their templates are limited and focused primarily on long-form content type outputs. So far this has been an uber frustrating journey.
Yes, the problem with my niche is that there is hardly any information in the top 10 serps, only some pinterest images and some YT videos and some ecommerce sites. So to generate some useful content the AI needs to have some real world knowledge which is not available in training data. However I think we might get to a point where AI models will be able to process real time data that is unstructured and in any form. That is going to require huge resources and the current hardware may not support it.
 
Yes, the problem with my niche is that there is hardly any information in the top 10 serps, only some pinterest images and some YT videos and some ecommerce sites. So to generate some useful content the AI needs to have some real world knowledge which is not available in training data. However I think we might get to a point where AI models will be able to process real time data that is unstructured and in any form. That is going to require huge resources and the current hardware may not support it.
I agree. I think we'll get there one day. Possibly sooner rather than later. There's so much movement going on around this topic. Ai content marketing is the future and everyone wants in. I'm just going to make do for now with what's available, because it's better than nothing, and try to get in as a beta tester/early user of the next generation of services.
 
This is GPT-3, correct?

It is nice, but it can't produce original content. It just regurgitates the common knowledge it learned online.
 
Are you going to share the tool bro? You could at least have 20 BHW members test it out and make recommendations.
 
Back
Top