Think I might write another book, but this time with more GenAI assistance…
I have been excited with all the ways that GenAI tools have been able to help me edit my current book, and it excites me about what more I could do. I really want to go back revisit the concept I wrote about in a post last year regarding using video interviews as a source of analysis for insights. Specifically I was thinking about writing a book or maybe a short series of articles on the evolution of battlefield technology in the Ukraine war. There is ample content in the form of online interviews on this topic, from the front lines to the development labs. Not that there is a shortage of existing written content that discusses this topic, but that’s mostly the point. To see how fast it is possible to pull together meaningful long form content from a larger source repository of audio-visual content.
I have talked numerous times about the capabilities that GenAI will bring to both the commercial and defense sectors, but one of the critical things lacking in large supply currently is dual-use examples of GenAI technology for critical analysis. There’s lot’s of pontificating that goes on in defense intelligence circles about what GenAI could do, but precious little demonstration of that capability in action to prove it. Retrieval Augmented Generation (RAG) is useful, but it’s more of just a technical solution to a search problem, rather than a proof of larger analytical capability with a given model. It’s much more interesting to prove highly detailed insights via long form content, than just show contextual search capability with short responses.
The closest examples to this concept would be some of the work that is being done currently with GenAI in the legal field. Using the technology to speed research and write supporting documents for legal proceedings. There are plenty of examples of this going horribly wrong as well, and there in lies my interest. Where the user error begins, but technical capabilities continue, is a realm of new possibilities. All that’s required is a better understanding and employment of the technology to unlock those distant edge cases of the current level of the technology. Of course we are talking about a technology that is continually improving as well, so what better way to stay at the bleeding edge of capability than to explore its more difficult challenges?
