I never got around to it, and I was going to write about how my birthday went last week, but I just experienced a kind of “Eureka” moment. It was a nice day where Jen and I went to brunch at Original Pancake House, did a bit of shopping for pants and other necessities, and then had dinner at Baxter’s Grille. I had a ribeye (of course) and I indulged myself with their flourless chocolate truffle cake.
This is a verbatim conversation I had with an older LLaMa 3 model hosted on my PC via Ollama a few days ago. It started because I wanted a translation for the name of an X account named gatos fazendo gatices, and it just kind of spiraled from there. The topic eventually touched on how AI could be improved, the effects on society, and the nature of cognition itself.
It’s clear the LLM has a tendency to restate the question as part of the answer, or at least mine was.
Remember this guy?
Robo-Postgres returns!
AI is all anyone talks about these days, isn’t it? Even when it comes to databases like Postgres, devs are finding new and innovative ways to leverage LLMs in everyday use cases. Can you really blame them though? This is an exciting new technology that will transform how we work and potentially society as a whole once it finally matures. We even covered building a crude RAG app a few short weeks ago.
Has it really come to this?
AI is everywhere these days
Postgres and AI go together like elephants and chocolate. At first glance, it seems like a silly combination. Postgres is an RDBMS for storing data with ACID compliance, functions, views, and maybe some extensions or foreign data wrappers. Where is room for AI in that? It may be trendy to take something, rub some AI on it, and then declare it a breakthrough technology, but that isn’t necessarily reality.
AI has reached an inflection point that I feel should be concerning to anyone who works in a white-collar job. The capabilities of natural language and creative-based AI engines were often ridiculed over the past few decades, but recent advances have changed the picture substantially.
The reason I say this isn’t really what most would assume. The problem in a nutshell, is that while current AIs are not perfect, the sobering realization is that they don’t have to be!
