The Implications of Prompt Interfaces (Vol. 7)

“Programming is becoming less abstract. We can actually talk to computers in high bandwidth in natural language. We’re using the technology, and the technology is helping us understand how to collaborate with it versus ‘program’ it.” -? Mira Murati, CTO of OpenAI

This week, we dissect this single, wonderful thought from Mira Murati about prompt engineering…

Natural language helps programming become less abstract.

When developers use natural language to write and troubleshoot code, it can help break down expression barriers. Language makes it easier to express concepts and generate ideas.?

For example, vector databases that feature a? natural language interface help developers explore data, develop hypotheses, and evaluate data quality more directly than with SQL, Python, R, PHP, or C#.

Read Where Do We Go From Here, a conversation with Mira Murati and Martin Casado, for a great discussion of how natural language helps make some coding tasks less abstract.?

Conversational interfaces help humans get into a flow state.

Flow state, a term coined by psychologist Mihaly Csikszentmihalyi in the 1960s,?is a cognitive state where we’re immersed in creativity, where “Every action, movement, and thought follows from the previous one, like playing jazz. Your whole being is involved, and you’re using your skills to the utmost.”

Prompt and chat-based interfaces help programmers stay in a flow for longer. Some find they generate more ideas and better ideas, too.

Read What Builders Talk About When They Talk About AI on the Andreessen Horowitz blog, A16Z.com, to hear some leading developers talk about reaching a flow state with prompt engineering.?

Prompting helps us collaborate with computers versus ‘programming’ them.

Prompting provides a more collaborative experience compared to writing hundreds or thousands of lines of arcane computer instructions. By simplifying the interface to code, team members who are not as coding-savvy can more easily participate. For example, data engineers can evaluate data output without sorting through Java code, and ML engineers can test and evaluate models without getting bogged down in coding detail.?

For a fun exploration of the world of prompt engineering, watch this A16Z podcast episode with Guy Parsons, author of The DALL-E Prompt Book: Unlocking Creativity with Prompt Engineering