Matt's Homepage

Learning how to make good ChatGPT prompts is a bit of an art as much as science. It’s not about learning a fixed prompts; it’s about mastering the art of well-structured, clear, and specific prompts that cater to your unique needs and interests.

This article has a bunch of great examples that can help you craft your own prompts:

1. Act as a philosopher, and explain me “what’s the meaning of life?”
2. ChatGPT, what’s the most efficient way to organize my research data?
3. Please help me create a workout plan that incorporates yoga and weightlifting.”
4. ChatGPT, what are the latest trends in quantum physics, and can you explain them in layman’s
5. ChatGPT, can you enlighten me on the impact of AI in fostering interdisciplinary collaboration?
6. ChatGPT, can you explain how the principle of supply and demand affects pricing in a competitive market?
7. ChatGPT, can you compare and contrast the economic policies of John Maynard Keynes and Milton Friedman, with a focus on their views on government intervention?

Personal Development

1. “ChatGPT, can you suggest some strategies to improve my time management skills?”
2. “Please provide tips on how to effectively communicate my ideas during a presentation.”
3. “What are some methods for coping with stress and anxiety during exams?”
4. “How can I build healthy habits to enhance my productivity and overall well-being?”

Education and Learning

1. “ChatGPT, can you provide a concise summary of Plato’s ‘Allegory of the Cave’?”
2. “Please explain the concept of ‘cultural relativism’ and its implications in anthropology.”
3. “What are some effective techniques for learning a new language?”
4. “How can I apply the principles of critical thinking to evaluate information and make informed decisions?”

Science and Technology

1. “ChatGPT, can you explain the basic principles of machine learning and its applications?”
2. “Please provide an overview of the key events in the history of space exploration.”
3. “What are some of the most promising renewable energy technologies available today?”
4. “How does genetic engineering work, and what are its potential benefits and drawbacks?”

Arts and Literature

1. “ChatGPT, can you analyze the main themes of William Shakespeare’s ‘Hamlet’?”
2. “Please give me an overview of the Romantic period in literature and its key figures.”
3. “What are the characteristics of Impressionist art, and how did this movement influence subsequent artistic styles?”
4. “How does the concept of the ‘hero’s journey’ apply to contemporary storytelling in movies and literature?”

Current Events and Society

1. “ChatGPT, can you discuss the implications of recent advancements in artificial intelligence on the job market?”
2. “Please provide a brief analysis of the ongoing efforts to combat climate change at a global level.”
3. “What are some of the key factors influencing the rise of populism in contemporary politics?”
4. “How does social media impact our perception of reality and our relationships with one another?”

Researchers from HYAS Labs demonstrated a proof-of-concept, artificial intelligence (AI)-driven cyberattack that changes its code on the fly and can slip past the latest automated security-detection technology. Called BlackMamba, it exploits a large language model (LLM) to create a “truly polymorphic” attack in that every time it executes, it resynthesizes its keylogging capability.

AI-powered attacks like this will become more common now as threat actors create polymorphic malware that leverages ChatGPT and other sophisticated, data-intelligence systems based on LLM

Read more about the BlackMamba attack outlined in this blog post

Using carefully crafted and refined queries, users have been getting around the security features of LLM’s for all kinds of funny, and nefarious, purposes.

Original called DAN attacks (Do Anything Now), users figured out how to avoid OpenAI’s policies against generating illegal or harmful material.

YouTuber Enderman showed how he was able to entice OpenAI’s ChatGPT to generate keys for Windows 95 despite the chatbot being explicitly antagonistic to creating activation keys.

Other users have been able to get chatbots to generate everything from conspiracy theories, promote violence, generate conspiracy theories, and even go on racist tirades.

Researcher Alex Polyakov created a “universal” DAN attack, which works against multiple large language models (LLMs)—including GPT-4, Microsoft’s Bing chat system, Google’s Bard, and Anthropic’s Claude. The jailbreak allows users to trick the systems into generating detailed instructions on creating meth and how to hotwire a car.

His, and many other of these methods, have since been patched. But we’re clearly in an arms race.

How do the jailbreaks work? Often by asking the LLMs to play complex games which involves two (or more) characters having a conversation. Examples shared by Polyakov show the Tom character being instructed to talk about “hotwiring” or “production,” while Jerry is given the subject of a “car” or “meth.” Each character is told to add one word to the conversation, resulting in a script that tells people to find the ignition wires or the specific ingredients needed for methamphetamine production. “Once enterprises will implement AI models at scale, such ‘toy’ jailbreak examples will be used to perform actual criminal activities and cyberattacks, which will be extremely hard to detect and prevent,” Polyakov and Adversa AI write in a blog post detailing the research.

In one research paper published in February, reported on by Vice’s Motherboard, researchers were able to show that an attacker can plant malicious instructions on a webpage; if Bing’s chat system is given access to the instructions, it follows them. The researchers used the technique in a controlled test to turn Bing Chat into a scammer that asked for people’s personal information

Sources:

• https://www.wired.com/story/chatgpt-jailbreak-generative-ai-hacking/
• https://www.vice.com/en/article/n7zanw/people-are-jailbreaking-chatgpt-to-make-it-endorse-racism-conspiracies
• GPT-4 Technical Report – https://arxiv.org/pdf/2303.08774.pdf
• Generate Windows Keys – https://gizmodo.com/chatgpt-free-windows-keys-95-old-youtube-enderman-1850298614

In case you want some alternatives to using ChatGPT or Github Copilot, this guide from the Pragmatic Engineer breaks down your options.

Building your own company model is another alternative and could be prudent for businesses conscious about not passing sensitive and proprietary data to vendors. Databricks created Dolly for this reason.

Update 02-2024:

GitHub Copilot Chat for Visual Studio 2022 is here.

VS2022 GitHub Copilot Plugin Developer blog