Reminds me of the ship of theseus philosophical experiment where they replace neurons by logic gates one by one and ask when exactly consciousness stops existing.
Hmm, why not? For the astable configuration, you could use a 100F capacitor with R1 = 10 Meg and R2 = 7.5 Meg, for a 55 year period. Base current for the Threshold NPN will come from the Trigger PNP (and hopefully temperature drift matches OK). Other than maybe the 100F capacitor might have some variation in capacitance and leakage current over the course of 55 years ;-)
I really want to build one of those, they look great fun. (specifically in context of the article I want to see what happens if you lower the CG. Harder balance problem, but might reduce some of the instantaneous torques)
Without benchmarks and/or a whole suite of non-cherrypicked examples, this means nothing because you can trivially make an AI generate anything from text.
im def working on benchmarks for how my own general harness improves task performance vs same model in a commodity setup. its hard to do!
i will say that my current harness: https://github.com/cartazio/oh-punkin-pi is a testbed for a bunch of 2nd gen harness tech, largely optimized for reasoning llms only. the next one after this harness is gonna be epicccc
reply