decades later semantic layers are still a good idea. will the value they provide agentic ai finally be the reason enterprises build & maintain these valuable business context dictionaries?
Tag Archives: artificial_intelligence
don’t lead your chat-based llm (it wants to please)
ai tools want to please us, but their overly-agreeable responses are tweaked to make use happy, not necessarily provide the right, or best, response — don’t trust the response at face value!
yarp: yet another rag post (this time using sql)
you don’t have to know python or bother your data scientists to start exploring genai concepts like rag; you just need a tool that offers these features in a familiar sql interface
unstructured docs in ai (the wild west)
rag ai apps can only be as good as the parsed and chunked data that fuels them – testing, testing, and more testing the outputs of all the various available libraries with the front-end apps is critical
optionality and common sense (why i returned to starburst)
i’m so excited to have returned to starburst and be focused on rebooting the devrel function, not to mention staying active in the trino and iceberg communities — long live the icehouse
the effect of ai on intelligence (behold the idiocracy)
the long-term benefits of sunscreen have been proved by scientists whereas my advice on ai has no basis more reliable than my own meandering experience; i will dispense this advice now, but trust me on the sunscreen
wait… what? (a video game named lester)
i always thought it was super cool to have some lester (kasai) skateboards and stickers, as well as garbage pail kids sticker with my name on it, but today i found the coolest thing ever – a video game using my name
finally checking out chatgpt (adding a new tool in my toolbelt)
putting aside my (natural?) fear of artificial intelligence, i finally got around to exploring (testing?) chatgpt that everyone has been talking about for many months now