The Efficient Frontier of AI
Every portfolio manager knows the efficient frontier - the set of optimal portfolios offering maximum returns for given risk levels. What if AI prompts had their own efficient frontier?
As we all start to use AI, prompt optimization will be a consistent challenge. GEPA, GEnerative PAreto, is a technique to discover the equivalent efficient frontier for AI.
Reading the paper, I noticed the initial results were promising, with a 10-point improvement on certain benchmarks & a 9.2 times shorter prompt length. Shorter prompt length, & we all know that input prompts are the biggest driver of cost (see The Hungry, Hungry AI Model). So, I implemented GEPA in EvoBlog.
To use GEPA, we must identify the scoring axes that an LLM uses to score a post. Here are mine :
Now that we have this framework, we can enter a prompt to generate a blog post & have the EvoBlog system iterate through different prompts to meet the efficient frontier for each dimension, weighted across all variables—not just one.
Here are the scores for two hypothetical blog posts. You can see one spikes more on style, while the other one focuses on data usage. Using GEPA, we can determine which is the better all-around post. In this case, it is the data-focused post.
All of this to say, dear reader, that I’ve only ever published one blog post fully generated by AI.
My goal with these automated systems is to learn how they work, how to tune them, & generate initial drafts that approximate my first & second drafts. I will always be completing drafts three & four.
The efficient frontier is no substitute for insight & an authentic voice.
Venture Capital in Web3/AI/Fintech | Financial Modelling and Valuations | Consulting | Startup Coach
8hGreat you are not fully empowering AI and stay relevant
Managing Partner at ATD Homes
10hInvesting is a competition, and I wonder if as more enter, the 10% doesn't shrink . Never look for the homerun, hit the singles, and keep your principle.
Senior IT Consultant | Empowering Financial & Public Sector Teams with Data-Driven Decisions | Expert in BI, SQL, Azure, & Power BI | Turning Complex Data into Strategic Insight
21hThis is such an insightful post! I really appreciate how you connected the concept of the efficient frontier to AI prompt optimization — that’s a powerful analogy. The GEPA approach sounds fascinating, especially with the measurable improvements in prompt length and performance. Love the emphasis on keeping the human element intact — using AI to accelerate first and second drafts, while preserving authentic voice in later drafts. Truly a great perspective for anyone exploring the future of human-AI collaboration!
| MBA Cybersecurity Leadership | Product Management - Agile & Lean | Strategic Growth + Product Operations in Tech & Trade | Cybersecurity in Product Lifecycle. Driving Creativity & Innovation. |Stafford, TX, USA |
21hThe progression from efficient frontiers to GEPA to the input-output economics is genuinely illuminating. It is a great example of how foundational insights from one domain can unlock entirely new approaches in another. The connection between context optimization and measurable outcomes is a powerful insight. Thank you Tom!
Founder @ Rise Productive | Content Creator & Agency Owner
21hThat's a cool way to look at it, for sure. Makes a lot of sense for getting better results, ya know?