Until you've tried using an LLM assistant fully hooked into a stateful REPL, you can't speculate. The experience is fantastic as the feedback for the code being developed is earlier and tighter.
The LLM agent will often write the code for a function and immediately follow that code up with several smoke testing expressions and the eval the whole thing in one go, function and tests.
It will creatively setup test harnesses to enable it to exercise code while it's being developed. (think html endpoints, starting and stopping servers, mocking)
And it goes on from there. Its an experience, and I submit to the reader that they experience it sooner than later bc its an extremely effective workflow and its AWESOME!
I wasn't sure how to chain function calls so had to look that up to implement movei, but apart from that was fairly straightforward (it's (do (<func1>) (<func2>) ...)).
Sorry but dependencies are choices. Rewriting on a new stack with less dependencies is just choosing less dependencies. People seem to believe that using React requires using all the other shiny libraries. Right sizing your implementation to your needs is important. But it’s not Reacts fault, it’s the false impression that you can accrete things without cost.
I appreciate your enthusiasm and agree that your stated goals are important. But if you are serious about this project having an impact, you may want to get some feedback and help with the voice of your presentation. You talk of saving the world, but you are mainly talking about "you" saving the world. It comes across as grandiose ... Please speak clearly about your project and its specifics and less about you if you want people to listen.
Very good point. I'm not sure I ever said 'I' in that context, I certainly don't mean so.
I see myself as just the campaign manager for the World Brain, and one of the first coders of this component of it. The World Brain, is you.
Others working on open hardware, hardware mesh net (wireless, Etc.), Etc., all of these people have already done just as much as I or more in making necessary components. So it certainly isn't about me. In this post-Snowden world, so many people know exactly what to do now, it is amazing really, so many people united and working together and knowing exactly what is needed!
Thanks for that input still! I will consider that in how I word stuff in the future. I am just /very/ excited about what I've already calculated as a certain path and inevitable future for humanity.
I found out late in my coding (only 2-3 months ago) that H.G. Wells certainly beat me in 1937 to the idea, no, realization, of a unified human consciousness :) (See his essay entitled World Brain.)
The LLM agent will often write the code for a function and immediately follow that code up with several smoke testing expressions and the eval the whole thing in one go, function and tests.
It will creatively setup test harnesses to enable it to exercise code while it's being developed. (think html endpoints, starting and stopping servers, mocking)
And it goes on from there. Its an experience, and I submit to the reader that they experience it sooner than later bc its an extremely effective workflow and its AWESOME!