However agents (not just LLMs) were definitely involved.

It’s possible I misunderstood your question.

Basically it allowed me to easily spin up a highly usable front-end as well as scrape together a large dataset to back it. The dataset is industry specific knowledge that does not exist in any public, single source. Part of this dataset creation was generating geolocation polygons based on legal documents that verbally defined physical territory. Absolute precision is not necessary for our purposes, but as far as we have confirmed so far the agent basically one-shotted the data with negligible errors and sufficient precision.

Humans were involved in the process, but there is zero chance this project would have happened without agents. The dataset alone would have taken weeks of full time effort. The front end would have been easier, but still time consuming.

I don’t really understand how people aren’t seeing the value in this.

The US civil war is the most explicit demonstration of this process. Northern industrial capitalists ended the southern agrarian slave economy, increasing market size and generating extreme wealth in the latter half of the 19th century.

But, you know, that’s just a guess.

At some point you need to forcefully take the things from the people who own them now and give them to the one-world government.

Position 1: a human is an entity distinct from their family.

Position 2: a family is an entity that exists across generations, and no individual in the family can be abstracted from it.

I don’t think you two, or anyone else, is ever really going to suddenly change their mind on this point. It’s at the foundation of the irreconcilable divide between leftism and conservatism.

Ultimately, since we have plenty of evidence to show that people will just shout past each other when they hit this ideological sticking point, I think a better approach would be to individually answer the question: “Which is a better model for predicting the world?”

The reaction to the US government restricting access to foreign nationals is interesting to me. On the one hand, people rail against US imperialism. On the other, they get angry when they don’t have access to the tools of empire. It feels very “What have the Romans ever done for us?”

I believe this lying is probably what you mean when you say in your other writing that you should adopt beliefs that benefit you rather than those that are true. I find this morally reprehensible.

He gives some rather cute examples, like the language of Finnegans Wake by Joyce being very low redundancy (high efficiency in your words). He also states that crossword puzzles don't work in a perfectly efficient language, that 50% redundancy is pretty good for 2-d puzzles, and 33% redundancy good for 3-d puzzles. This has always been one of my favorite and in my mind most random corollaries in a paper.

https://people.math.harvard.edu/~ctm/home/text/others/shanno...