I built my first commercial LLM agent back in October/November last year. As a newcomer to the LLM space, every tutorial and youtube video was about using LangChain. But something about the project had that "bad code" smell about it.

I was fortunate in that the person I was building the project for was able to introduce me to a few other people more experienced with the entire nascent LLM agent field and both of them strongly steered me away from LangChain.

Avoiding going down that minefield ridden path really helped me out early on, and instead I focused more on learning how to build agents "from scratch" more or less. That gave me a much better handle on how to interact with agents and has led me more into learning how to run the various models independently of the API providers and get more productive results.

I saw very many from near conception when they were applying for very first funding.

Don't get me wrong, regulation is a serious topic, but for startups outside of specific domains such as healthcare, it is not realy a thing that seems to stop people from entrepreneurship.

Part of that is certainly that startups just don't care that much and have a we'll worry about that once we are making our first 10 million arr attitude.

I sense a business opportunity: Euthanasia as a Service. EaaS. With an API.

Being impressing or otherwise is very subjective.

SQL (ACID) over multiple non-cache-coherent nodes is extremely difficult to pull with regards to consistency, though.

I wouldn't recommend JVM for web in 2023, but if you really want to use it, I would at least recommend Kotlin.

It has a better syntax, more up to date tools and is officially supported by JetBrains too. It also has the Ktor framework which is really fun to work with.

Such a textbook example of confirmation bias. You have certain conviction, and you dig deep until you find some references to it, and then declare that your conviction is vindicated.

My conviction is that the growth in corporate profits is driven primarily by technology advance and globalization. And no, globalization is not a one way street, only benefiting corporates. China achieve their economy growth and their status as superpower, lifting a billion people out of poverty, thank in no small part to the large and rich market of developed countries they've been able to access.

The growth is slow down because temporary roadblocks such as the pandemic and financial measures countries adopted to counter it. Geopolitics also play a role. Globalization is well and alive still, and while it will evolve, it is not reversible. We will not go back to the world pre-1990s.