Use a conversational interface and start with any prompt
Follow up with better and more specific questions and narrowings
Experiment with length, technicality, and accessibility
Set constraints to prompt creativity
Use persona prompts to shape the AI's behavior
Remember that the AI has no personality and no real knowledge or fun
Practice programming and iterate on the outputs
Be aware of the AI's limited memory and start a new chat if necessary
Spend time and effort to become skilled at prompting
AI systems will become more tailored and adaptable in the future
Have realistic expectations and remember that the AI is a machine
Overcoming the tendency to be polite and ask for multiple versions takes time
The ease of use may decrease the transparency of the AI's processes
Anticipate that future AI systems may have fewer options but be more user-friendly
00:00
Transcript
Episode notes
ChatGPT, the artificial intelligence chatbot capable of generating human-like text, seems to be everywhere. But how trustworthy are these tools -- and what do they mean for the future of writing and work? Adam brings AI entrepreneur Allie Miller and innovation and entrepreneurship professor Ethan Mollick to discuss the capabilities of ChatGPT, debate its merits and downfalls, and ponder what we should -- and shouldn’t -- leave to AI. Transcripts for ReThinking are available at go.ted.com/RWAGscripts