So firstly let me state what this blog isn't about.

No, we are not going to talk about chat-gp3 taking programmers' jobs; because it won't

Nor are we going to talk about chat-gpt3 stealing all of the open-source code; because it does and that has been talked about to death.

What we are going to talk about is how chat-gpt3 is a threat to blogs like this one and how to protect your organisation's intellectual property (IP) and revenue from chat-gpt3.

Since I wrote the first draft of this article, Bloomberg has published an article suggesting that Microsoft is going to add chat-gpt3 to Bing, so this is no longer a theoretical threat

Bloomberg - Microsoft Hopes OpenAi's Chatbot will make Bing Smarter

you think it's a spider, but it turns out it's a wasp

Chat-GPT3 is many things but what it shares in common with every other information aggregator is that it is a website crawler or what is commonly called a spider.

To build its knowledge base, it needs vast amounts of information. As has been discussed to death, it crawls sites such as github for open source code but it also crawls every other site, such as this blog as well as any public websites that you or your organisation publish.

a better search engine

I have now read a number of articles discussing the possibility that chat-gpt3 will replace the likes of google search.

I can see the argument here, the Q/A style of interaction is certainly more verbose but the chat-gpt3 engine can often get to that 'nub' of information that you require much faster than a google search. The ability to make 'in context' follow-up questions is also really nice.

So If chat-gpt3 is better than google search, why wouldn't Open AI launch chat-gpt3 as a search engine and take all of Google's juicy advertising revenue?

The answer is that they won't because we are going to stop them from doing it!

And we should stop them from doing it; starting today.

no, I am actually sane

No I haven't lost my mind; here is why and how we are going to stop them.

If you are anything but a newbie to programming you will know that Google crawls every website in the world on a regular basis.

In fact, as developers, we often invite google into our site by publishing a sitemap. A sitemap is an XML, Text or RSS file that tells Google what pages we want to be indexed.

One of the first actions we did when launching OnePub was to publish a sitemap to Google so that it would index our site and we would start showing up in organic search results.

I write this blog, not for you, dear reader but rather for Google.

The primary objective of writing this blog is to achieve a high ranking in organic search results for the keywords that our Team want to be associated with OnePub.

I only attempt to inform and entertain you so that you will share/link and visit this blog again so that Google thinks that OnePub is a great site to send people to if they are interested in a Dart private repository SaaS (see I did it again).

The fact that you get some useful information out of reading this article is purely a secondary objective (sung to the tune of 'you're so vain' by Carly Simon).

All I care about is that you fertilise the Google search index.

You might say that there is an implied contract between you, my little worker bee, and this blog.

I give you useful information and hopefully, you will share that information, visit me again and possibly talk about OnePub with a colleague.

In the same way, there is an implied contract between Google and me.

Google gets to crawl my website and show results that mention OnePub. Some of those users will click the link and visit the OnePub website where they can read about Dart and come to the realisation that OnePub is a fantastic private SaaS repository for Dart (did you even notice me doing it this time?).

Google gets advertising revenue by being able to index the OnePub blogs and in exchange, I get visitors to my site that will hopefully sign up for OnePub and pay me some money.

Just like the flower and the bee, it's a mutually beneficial relationship.

enter the wasp

Chat-gpt3 is something else altogether.

A better analogy might be the Spider Wasp, a wasp that hunts spiders.

The Spider Wasp hunts spiders but rather than killing the spider, the wasp paralyses the spider.

Some species of Spider Wasp are known to bite off the legs of larger spiders to make them easier to handle once paralysed.

The wasp drags the spider back to its burrow and lays a single egg on the body of the spider and leaves the spider until the egg hatches.

Once the egg hatches, the larva starts eating the still-living spider.

The hatchlings know which parts of the spider to eat first so that the spider stays alive for the longest time possible and remains fresh.

Just in case you were wondering, yes, this is yet another of Australia's delightful fauna.

a purely parasitic relationship

Unlike the flower and the bee, there is no symbiotic relationship here, the spider gets nothing from the arrangement except a slow torturous death.

And the same goes for my blog and chat-gpt3.

Chat-gpt3 will crawl and index the OnePub blog, taking all of my valuable intellectual property (IP) and incredible insights :D

When one day someone asks Chat-gpt3 - 'how is chat-gpt3 like a Wasp Spider', chat-gpt3 will quote my article (because who else would make such ridiculous analogies) without attribution.

But what it won't do is offer the user a link to the source of the information and it will never result in a user visiting the OnePub blog. The result is that no chat-gpt3 user will ever sign up to OnePub as a result of reading this blog and hence I will not generate any revenue, so why would I keep doing it (OK, so the ego thing might be sufficient motive)?

The contract has been broken, chat-gpt3 is a parasitic wasp, not a helpful garden spider.

we can stop it now

So how do we stop ourselves from being the spider in this story?

I think Charlotte's web must have had a profound effect on me as a child, as I've written a few stories over the years where a spider was the protagonist. It now occurs to me, that in all of the stories, a female was the villain, do I have mummy issues?

chat-gpt3 to the rescue

Ironically, chat-gpt3 can help us to thwart its evil designs:

Me> how can I block chat-gpt3 from crawling my website?

Chat-gpt3> There are a few different methods you can use to block the "chat-gpt3" user agent from accessing your website. Here are a few options:

1. Use the robots.txt file: As I mentioned earlier, you can use the robots.txt file to tell the "chat-gpt3" user agent not to crawl your website. To do this, you can include a User-agent directive followed by the name of the user agent you want to block, like this:

User-agent: chat-gpt3
Disallow: /

It's important to note that the robots.txt file is a suggestion to web crawlers and bots, and not all software applications that access the web will honour the instructions in this file. Some web crawlers may still access your website even if it is disallowed in the robots.txt file.

1. Use a .htaccess file: If your website is hosted on an Apache web server, you can use a .htaccess file to block specific user agents. To do this, you can add the following code to your .htaccess file: RewriteEngine On RewriteCond %{HTTP_USER_AGENT} chat-gpt3 [NC] RewriteRule .* - [F]

This will block all requests from the "chat-gpt3" user agent.

Me> how do I block the chat-gpt3 agent using nginx?

Chat-gpt3> To block the "chat-gpt3" user agent using Nginx, you can use the nginx.conf file to create a rule that matches the user agent string and returns a 403 Forbidden response.

Here's an example of how you can do this:

Open the nginx.conf file for your website. This file is typically located in the /etc/nginx directory.

Add a new location block to the file, like this:

location ~* (chat-gpt3) {
    return 403;
}

consequences and conclusions

So here is the rub, I actually think the likes of chat-gpt3 is likely to be a useful tool that could improve the condition of the human race.

It can help non-domain experts gain access to knowledge in a simple and intuitive manner whereas with google you tend to need some domain expertise to even know how to ask the right question.

The problem is that chat-gpt3 relies on the creation of knowledge by third parties. Without some equitable compensation model there is no incentive for those third parties (I'm talking about me here) to create that knowledge and share it with chat-gpt3.

Of course, the real irony is that chat-gpt3's very existence will reduce the sources of knowledge (e.g. blogs) that it relies on.

In the end, chat-gpt3 is both the spider and the wasp.

Chat-gpt3 is a double edge sword - whether a model can be found that provides equity and allows the creation of knowledge in the public to continue remains to be seen.

In the meantime; the vandals are coming, lock your daughters away.