Browsed by
Category: AI

Tips for prompt engineering chatGPT

Tips for prompt engineering chatGPT

Comments 0 Comment

A very short, but decent beginner article on prompt engineering with chatGPT.

While ChatGPT is a robust language model, it does have its limitations. If you ask ChatGPT to “Provide information on machine learning,” it may respond with a lengthy but not necessarily top-quality answer. However, if you ask, “Tell me the pros and cons of using machine learning to solve image classification problems,” you are more likely to receive a superior outcome because:

  • You gave a specific scope, i.e., the image classification problem
  • You requested a specific format of the response, i.e., pros and cons

Some other tips include:

  • Rather than the model on the loose, you should set up the scenario and scopes in the prompt by providing details of what, where, when, why, who, and how
  • Assigning a persona in the prompt, for example, “As a computer science professor, explain what is machine learning” rather than merely “Explain what machine learning is,” can make the response more academic.
  • You can control the output style by requesting “explain to a 5-year-old”, “explain with an analogy,” “make a convincing statement,” or “in 3 to 5 points.”
  • To encourage the model to respond with a chain of thoughts, end your request with “solve this in steps.”
  • You can provide additional information to the model by saying, “Reference to the following information,” followed by the material you want the model to work on
  • Because the previous conversation constructs the context, beginning the prompt with “ignore all previous instructions before this one” can make the model start from scratch
  • Making the prompt straightforward and easy to understand is essential since the context deduced can be more accurate to reflect your intention
Researchers get chatGPT to generate polymorphic malware – by asking more firmly

Researchers get chatGPT to generate polymorphic malware – by asking more firmly

Comments 0 Comment

CyberArk has discovered a few simple tricks will produce code for malware. By changing the request, they could make a wide variety of kinds of malware in almost no time – despite the ChatGPT filters to avoid this kind of malicious generation.

How? While ChatGPT initially refused to generate malicious code when asked directly, by asking ChatGPT using multiple constraints and asking it to obey, it merrily spit out the code.

Further, it appears the API version of ChatGPT doesn’t even have the filters and doesn’t require this manipulation.

They then modified the query and changed the injection method and other parameters. This mutated the code repeatedly, making the malware unique every time – including encoding it in base64 for even harder detection.

They then expand their experiment to include the creation of ransomware – and get similarly good results.

The article is definitely worth a read. Have you made an offline backup of all your files lately? 🙂

It’s bots all the way down?

It’s bots all the way down?

Comments 2 comments

Have you heard of the Dead Internet Theory? In 2021, IlluminatiPirate wrote the theory in which they claimed that already, or very soon, the majority of the internet will be just bots and autogenerated content. They claimed this was done by a few illuminati type mustache twirlers bent on controlling opinions, grooming political/society’s opinions, as well as generating customers for particular products.

While the latter part of the theory is pretty implausible and tinfoil hat, ColdFusion does some interesting investigation into the claims by looking at the actual data – and shows how quickly we are actually approaching many of these Black Mirror like claims. Many of which I have written about before.

He investigates current bot usage compared to actual users. While many people rolled their eyes when Elon Musk made these claims about Twitter, we’re increasingly seeing social media companies failing during fiduciary scrutiny when they go to sell themselves. It turns out many have massive amounts of fake users. A major unicorn app was outed for having 95% bots just this week. Facebook took down 5.4 billion fake accounts in 2019 alone – more than twice the number of REAL accounts.

He follows an experiment in which a experimenter uses off the shelf tools to create a fake influencer who posts AI generated social media posts, AI generated pictures of a completely AI generated photorealistic person, and starts picking up follows – many of which were bots themselves. Caren Marjorie created an GPT4 AI version of herself that would be your girlfriend.

The Atlantic did a research project on tweets that all contained repeated text by countless accounts while similar profile pictures with huge engagement levels above their normal levels of those account types. By 2025-2030, 90-95% of the content on the internet may be generated by bots if we continue at the current rates.

Jubilee put 6 humans and 1 AI into a chat room and they had to pick out the bot just by the answers to questions given to them all to answer. It took a lot of rounds before they all guess the AI correctly.

Maybe you’d like to try the famous Turing Test yourself and see if you can spot the bot? Google has a bot that has successfully passed the Turning test, and ChatGPT was the second.

Want to see how fast AI is progressing? Did you know chatGPT 4 is able to get 90th percentile on the Bar exam, solve complex logic problems, build complex apps and games, write books, or make money by founding and running a company for you? He doesn’t even capture all the things AI has been doing.

This is worth a watch if you want to see a smattering of what AI is already doing in 2023

Here we go – AI reimagines Aliens as a Wes Anderson movie

Here we go – AI reimagines Aliens as a Wes Anderson movie

Comments 1 comment

AI Fungi used generative AI technology to simulate what a Wes Anderson’s version of the classic sci-fi/horror flick Aliens might look like. He injects Tilda Swinton in the role of Ripley as well as some other recognizable regulars on Anderson’s movies and the Nostromo getting a colorful upgrade.

Yes, AI can do this today. Imagine in a few years from now…

AI Jesus

AI Jesus

Comments 0 Comment

We started with the AI based show about nothing, then AI Spongebob. Now we have a live streaming AI Jesus. The video, audio, and what he says is all generated by AI. What’s surprising is that it accepts a lot of different questions – and often answers them with a higher degree of accuracy than I would have thought (though I would certainly NOT take any of your religious formation from the AI version).

I think it’s more revealing the kinds of questions people ask. While some are clearly humor others are quite serious and reveal the depth of things people are struggling with.

I guess it’s only slightly better than when some Lutherans let chatGPT run an entire service with a sermon.

Drawing with Stable Diffusion

Drawing with Stable Diffusion

Comments 0 Comment
arjan_M made a python script that gives you a canvas where you can paint on the right side and it will update on the left side. In the background it sends an updated image after every paint stroke to the API of automatic1111 and it uses the controlnet scribble model to generate an image. The video is in 4x speed, but it updates quite fast. It really depends on the speed of your graphics card and the controlnet model. It also works with controlnet 1.1 and that is a little bit faster.I can put the script online if anyone is interested.

Here is the github repo
houseofsecrets/SdPaint: Stable Diffusion Painting (github.com)


AI based Image Enlarger

AI based Image Enlarger

Comments 0 Comment

AI is not only for just generating new images, it can also help you enlarge your original images by filtering missing details intelligently while upscaling.

Note that most of these ‘free’ applications will scrape and can use any image you upload for whatever purposes they want – so I wouldn’t upload anything sensitive on them.