Supervised a project 2 week ago. Two programmers where hired to create an MVP. I have worked with both before.
- Alex from Germany. 100% code. 19 years experience.
- Hamid from Pakistan. Code + Copilot + GPT-4 + no-code. 4 years experience.
What do you think happened?
🚀 Define networked device access, execute commands (group/individual), use regex patterns for output, and set Influx tagging/keying for perfect measurements in #InfluxDB! How cool! 👍 https://t.co/q5mM0ojtZc
Jupyter AI, a new open source project, brings generative artificial intelligence to Jupyter notebooks with magic commands and a chat interface. Download it today to use hundreds of popular large language models, via @langchain, with your notebooks! https://t.co/MgzmUW8R8G
👶🤖 Introducing `gpt-engineer`
▸ One prompt generates a codebase
▸ Asks clarifying questions
▸ Generates technical spec
▸ Writes all necessary code
▸ Easy to add your own reasoning steps, modify, and experiment
▸ open source: https://t.co/NCSp8vsKA0
▸ Lets you finish a coding project in minutes.
@swyx scooped me on releasing first ❤️ – similarities to smol but many new innovations, check README.
Next, make it bootstrap. Which means:
A "gpt engineer" prompt should generate all functionality of the gpt-engineer repo itself.
GPT-Engineer is insane.
Simply specify what you want to build with a prompt, and the AI agent builds the entire codebase.
It's completely free and open-source, and it's already at nearly 17,000 stars on GitHub 🤯