Let's Make An AI Content Generator Based On GPT-2 (The OpenAI Model)

KevinRB said:
What amazes me, is that to date there has not been a SINGLE commercial script/software/plugin or subscription based service built around the GPT-2 releases....there is a hungry/insatiable market for content!.
Click to expand...

That's because it was built without a serious purpose in mind. It's more a "proof-of-concept" toy than anything else. Had the developers been serious about real content generation, you'd probably see what you're describing.

Bear in mind that there's an ungodly amount of work involved in serious content automation too. And by the looks of what this GPT2 thing generates, the people who made it took the easy route.
 
Advertise on BHW
I've tried to post ~100 articled generated by GPT-2 on my blog, not many results, continue to experiment. I think whoever will get reasonably good results will just disappear, and we will hear from them only when this niche will be completely depleted.
 
Harlet said:
This will never be shared as the person who develops it will have a goldmine, don't be ridiculous. There are Ai writing tools out there in the wild gaming the system as we speak. It will only be publicly available once AI is commonplace enough that it is no longer an edge. I'm a developer. I could make AI Writer. Real AI Writer is a whole different story, the people who are at the top of the market are at the top of the game period.
Click to expand...

exactly, it will be released only once its not really profitable to use it anymore cause there would be more advanced things out there or too many people would be using it so it wouldnt be profitable anymore.
 
Glad I found this thread. I've been working on a gpt2-based model for almost two months now. I'm using it to generate content for a niche site.

It took a lot of tinkering to get the thing to generate relevant content for 1 out of 10 generated articles (anywhere between 300-1000 words) and I usually get 1-2 paragraphs out of that single article.

I have two articles written with the help of my model each at about 1000 words. Each took about an hour to "write." I wrote 2 other articles for this niche site when I didn't have the model - it took 4 hours to write these 2 articles at about 600 words.

It still takes a lot of human intervention to get high quality content, but that might also help if detection is used to remove generated content. I really don't see how it's possible to do that reliably especially if a human edits as much as I have.

I might make a service out of it if I think I can turn a profit on what would be a substantial initial investment (need to build a rig capable of creating models fast enough for customers and their niches).

Anyways looking forward to hearing how other people are doing with this.
 
theRevolt said:
Nope, not really. See, there is gibberish ranking in lots of SERPs and the examples you get here are from an untrained model, so you could train the small model on a certain niche and you would get a better output.
Obviously, nobody will release a niche-specific highly trained model...

You may want to look up earnings reports, stock reporting etc... most of that is written by AI now and it ranks. That is obviously soft you're average spam blogger does not have access to.
Click to expand...


I think you and a lot of people are getting this area wrong, I don't know if Google would even penalize someone for using AI to generate content. All they want is the best content being delivered to the searchers. If this content is written by AI, a human, or a monkey, I don't think they care. The only reason they don't like the stuff generated now is that it is poor quality and utilizes whatever techniques to trick them. If you could produce college-educated niche-specific researched content with AI, that's great for Google. Their searcher is getting a great result. They could even possibly prefer this content in the future as they would know it has been checked for accuracy and combines an amount of research that could possibly take an entire human their life to accomplish.
 
Trained the medium version (355M) on my niche with decent results. Currently i'm training the big 1.5b version my dataset. This dataset contains articles i scraped from hundreds of sites in my niche. After that i polished the dataset with my programs. I know that this won't generate high quality articles by itself, but the cool thing is, that it generates thousands of articles in no time.

It only needs one small input of text targeting a Keyword in my niche and generates different outputs when rerunning with that input. So i plan to generate thousands of articles and automatically check their quality with something similar to the contentseochecker. Once it reaches a high enough score i have a SEO proof high quality article in my niche.

If this works, i'll let you know about it.
 
Morty073 said:
Trained the medium version (355M) on my niche with decent results. Currently i'm training the big 1.5b version my dataset. This dataset contains articles i scraped from hundreds of sites in my niche. After that i polished the dataset with my programs. I know that this won't generate high quality articles by itself, but the cool thing is, that it generates thousands of articles in no time.

It only needs one small input of text targeting a Keyword in my niche and generates different outputs when rerunning with that input. So i plan to generate thousands of articles and automatically check their quality with something similar to the contentseochecker. Once it reaches a high enough score i have a SEO proof high quality article in my niche.

If this works, i'll let you know about it.
Click to expand...
I've got a question but I can't PM you.

Could you please help me out with training the large model?
 
Thanks, I'm an idiot who isn't used with that ycombinator website and too lazy to research more
 
hossho said:
I think you and a lot of people are getting this area wrong, I don't know if Google would even penalize someone for using AI to generate content. All they want is the best content being delivered to the searchers. If this content is written by AI, a human, or a monkey, I don't think they care. The only reason they don't like the stuff generated now is that it is poor quality and utilizes whatever techniques to trick them. If you could produce college-educated niche-specific researched content with AI, that's great for Google. Their searcher is getting a great result. They could even possibly prefer this content in the future as they would know it has been checked for accuracy and combines an amount of research that could possibly take an entire human their life to accomplish.
Click to expand...
If you read my reply you'd see that I mentioned some examples where AI-generated content ranks highly as it is the BEST, because of mainly fact-based content. However, the current stuff is just subpar, and the ones that have something higher quality (custom trained model), of course, won't release it as it is $$$
 
theRevolt said:
If you read my reply you'd see that I mentioned some examples where AI-generated content ranks highly as it is the BEST, because of mainly fact-based content. However, the current stuff is just subpar, and the ones that have something higher quality (custom trained model), of course, won't release it as it is $$$
Click to expand...
Whoops, I wasn't clear here. I don't recall exactly what I was thinking then, but reading it now, I believe that I was agreeing with you and meant to quote the post you were replying to, but I don't remember. Either way, my bad, but I think we're both(as well as everyone in the forum) is in agreement that if one had the ability to produce AI created high-quality content for any niche, it would be a game-changer and cash cow because it would rank so well in a lot of places with ease. If you could do this, idk if you'd make more money writing papers for college students or in IM lol
 
cooooookies said:
Hi Mort, any updates on that?

Curiously following this thread and hoping for some wordpress-plugin which autoposts gpt2 content. This would be really amazing! And could be perfectly used to generated niche-relevant content for pbns: input: linking page's text, output: relevant content :)
Click to expand...
Hey coooooockies,
i found that even a trained gpt-2 1.5b on your niche doesn't produce a article that makes any sense. And i was only interested in such articles.
However a trained model can indeed be used to make full articles which uses keywords you want it to have, but i dont get why i shouldn't just use article spinners.
 
Yes, the articles do not make sense and are imho not really suited for money site content - although the back-bounces do not happen immediately, since the reader needs some time to understand that he reads bull. Ranking maybe still doable thereby.

Considering the quality, for 750M and 1.5B model the original gpt2 authors claim there is almost no difference. Maybe there is a difference when it comes to rarer keywords, but this another dimension.

For MS, an article spinner is currently much better. I would consider gpt2 content as search engine food - niche relevant, certainly. And that's the purpose I have in mind: filling/creating cheap PBNs automatically. Using low-impact, but niche-relevant pbn-domains which otherwise you would never consider to buy and fill.

Morty073 said:
Hey coooooockies,
i found that even a trained gpt-2 1.5b on your niche doesn't produce a article that makes any sense. And i was only interested in such articles.
However a trained model can indeed be used to make full articles which uses keywords you want it to have, but i dont get why i shouldn't just use article spinners.
Click to expand...
 
Advertise on BHW
You must log in or register to reply here.
Sign up now!

Main Menu

Home Main Forum List Black Hat SEO White Hat SEO BHW Newbie Guide Blogging Black Hat Tools Social Media Downloads

Marketplace

Account Selling Content / Copywriting EBooks / Methods Hosting Misc Proxies For Sale SEO - Link building SEO - Packages Social Media Social Media - Panels Web Design More

Making Money

Affiliate Programs Hire a Freelancer IM Journeys Making Money Pay Per Click Site Flipping Want to Buy

BlackHat World

Dispute Resolution Forum Suggestions & Feedback Introductions Lounge
Back
Top