In this Trends.vc Report, we talk about advanced prompting, how to guide AI to do complex tasks, top prompt engineering use cases and more.
💎 Why It Matters
The number of programmers just increased from 26 million to 8 billion.
🔍 Problem
You need to learn how to direct AI.
💡 Solution
Prompt engineering helps you get accurate and reliable results.
🏁 Players
Prompt Engineers
Prompt Engineering Tools
Prompt Engineering Use Cases
🔮 Predictions
- Victor Mustar made a Star Wars clip.
- Corridor Crew made a Rock, Paper, Scissors anime.
- Nick St. Pierre made a Sci-Fi movie trailer with his audience.
- Jon Finger made an action film based on an AI-inspired plot.
- Prompt Hackathon explores creativity with $5,000 in prizes.
- PromptHacks promotes prompt writing with $10,000 in prizes.
- Hack A Prompt boosts AI safety research with $37,500 in prizes.
☁️ Opportunities
- Kristian Fagerlie says ChatGPT can act like a financial, career or relationship expert.
- Alejandro Lopez-Lira and Yuehua Tang asked ChatGPT to act like a financial expert. It correctly interpreted financial news.
- Andrew Han built GPT3 Auditor which scans code for vulnerabilities. He asked AI to pretend it was the “world’s best cybersecurity expert”.
- Chain-of-Thought Prompting helps to come to complex conclusions.
- Few-Shot Prompting helps to adapt to examples and the context of the task.
- Zero-Shot Prompting helps to make predictions about unseen data without extra training.
- Jackson Fall set a budget of $100 to start a business.
- Matt Mic set the target location and citation rules for articles.
- Zain Kahn set the number of words, days and ideas for AI-generated answers.
- Riley Goodside asked a ”fast-talking wise guy from a 1940s gangster movie” to explain the bubble sort algorithm.
- Hasan Toor asked ChatGPT to “explain JavaScript like he’s 10 years old” and “curate ReactJS resources based on his skill level”.
🏔️ Risks
🔑 Key Lessons
🔥 Hot Takes
😠 Haters
“Prompt engineering is not programming.”
Backend-GPT is a language model that handles database and backend business logic. Similar to programming languages, you can prompt functions to work with data. Anyway, it’s too early to say that prompt engineering is programming. That’s why it’s a hot take.
“Prompt engineering will become obsolete once AI learns how to build its own prompts.”
We’re on track to this. AI can perfect itself without relying on human guidance. Tools like AutoGPT turn AI into an autonomous prompt building and execution robot.
“Tools built on top of APIs are just wrappers. They have no moat and can’t form a sustainable business.”
This critique has been around since the release of GPT-3. Danny Postma says if you can generate years of revenue in weeks or months, seize the opportunity.
“Marketplaces are winner-take-most markets. Why would we need more prompt marketplaces?”
These are micro-marketplaces which can optimize for niche use cases and audiences. While a micro-marketplace might not be the best option for most users, it's best for some. That's what matters.
🔗 Links
📁 Related Reports
Do you want to get the next Trends.vc Report? Join 50,000+ founders discovering new markets and ideas.