Discover more from The Threat Prompt Newsletter
TP#1 Prepare Yourself: Five Traps Lurking in AI Tech
Plus 7 Techniques for Reverse Prompt Engineering
Introducing the first edition of ThreatPrompt newsletter, where AI and Cybersecurity intersect. Every Saturday, I provide actionable insights to help you get the most from AI, while managing the risks.
First things first: what is the prompt in ThreatPrompt? Here is the definition straight from the horses mouth:
A prompt is a set of instructions or a statement that is used to guide or elicit a response from a person or machine. In the context of language processing, a prompt is a text or question that is presented to a language model, such as GPT, to generate a response. The prompt helps to define the context and topic for the language model's response.
Now, on to this week’s ideas…
Swyx breaks down exactly how he reverse engineered a new AI feature in a popular workspace tool to reveal the underlying prompts.
Learn how to create dynamic phishing campaigns in multiple languages with AI and how to use classification models to adjust and generate better responses to humans.
No knowledge in scripting? Don’t worry, english is good enough. Skip past the phishing walkthrough and get to the exploit code generation.
Impressive rhyme, for a common cybercrime. An idea generator for your next Cyber greeting card.
Avoid these traps and not only will your productivity with AI go up, but you’ll gain an edge in policy making for AI within your organisation.
Meet Procrasti-Blaster, a free AI powered service I created for fun to help people get unstuck. Try it out and let me know if it helped you.
Learn six types of information to include in your ChatGPT prompts to materially improve what you get back.
Click the emoji that best captures your reaction to this edition…
If your regulated business is struggling to get to market due to cyber risk, let me help you with Faster Cyber
New To This Newsletter?
Subscribe here to get what I share next week.