Insights on leadership, technology, and human-centered strategy, originally shared on LinkedIn and expanded for deeper exploration.
Two use cases for LLM today. 1) identify gaps between a more detailed description of work and the commitments made in an SOW. Propose changes. 2) summarize my own writeup such that each topic contains no more than 3 bullet points each no longer than 200 characters.
On PTO before starting my next consulting assignment. This time lift off in a bridged product and technical role. What I’m evolving into is in development, but I’ve come through the drama of an abrupt career shift and am forward focused. Hope. Pragmatism. Confidence. Humility.
That “Couldn’t hit a barn door with a banjo” is so common in English football as to be cliche tells you all you need to know about the joy and agony of human communication. We invent domain specific language in search of precision and out of vanity, to foster belonging and to exclude — but also because we simply love the sound of it.
Talking to Allyson Hernandez yesterday about how learning is both an existential joy and a place of vulnerability. How in-adeptness leaves me feeling insecure and a little sad. But I’ve found that if I set aside time while at the bottom of that curve to do something for which I have years of practice, it buoys my spirits and energy for the climb.
As with many things, it is a polarity. Leveraging the psychological safety earned through mastery to venture across spaces I do not know with confidence, patience, and humility.
The arc of tooling is to allow the tool wielder to focus on more context specific and valuable levels of abstraction. A carpenter doesn’t have to forge their own nails, they don’t have to hand plane their own beams to build a structure. (No one is saying they can’t if the context calls for it.)
The activities that generate value in software are understanding the problem. Solving it in ways that actually help users. With implementations that scale, evolve, and perform safely whenever needed.
Futurists can project how AI changes the nature of work and when. All that is observably true now, is that AI can — if used capably — help software professionals and craftspeople focus on these more context specific, valuable concerns.
My work involves taking decades of software engineering experience and applying it to domains where I have to build knowledge quickly. I rely on AI Tools, like the ChatGPT Large Language Model, to get my work done. Here’s a detailed experiment in prompt writing to make sense of the collision of regulatory, power industry, and legal terms of art. #generativeai #regulatorycompliance #businessintelligence
The most reliable use case for large language models (llm) I’ve found is culling through dense contexts of data and writing to produce answers based on prompts created by domain experts who then use that as input to their own data and experience informed analysis. It can drastically reduce time while leaving the human firmly in the loop.
Came up with a topic to propose for a journal article in my 30 min. walk to a conference. I need to get outside more.
Great conversation today with Neil Katz about how EyeLevel.ai’s tools improve the validity and relevance of responses from a Retrieval-augmented generation (RAG) LLM solution. Nothing more true than bad data produces bad results and that context improves relevancy. Nothing more familiar than structured metadata to help a machine create meaning.
It’s not that I’ve become more outgoing per se, it’s that my evolving acceptance of myself has enabled me to better disappear into conversation with others.
Just built ken-bot. A vector database in pinecone chunked from my public writings using langchain as the toolset. This makes the context for my openai request my own words. Now I can ask Ken-bot what I think about things.
I have come to believe that people, for the most part, are trying to get through their day. The cumulative effect is often cruelty. That we can work on. And, yes, there’s self-righteous ignorance and sociopathy. I’m privileged to not have to have to break bread with that.