[theschwa]

Between the clear writing and the diagrams, this was a great write up. I had actually skipped reading up on mHC as it sounded like it was going to take some time to grok, but this made it immediately approachable. I hope you do more write ups like this in the future.

[roywiggins]

imho the prose is very ChatGPT unfortunately

[E-Reverance]

> Residual connections are more than a trick to help gradients flow. They’re a conservation law.

> Not a hack, not a trick. A principled constraint that makes the architecture work at scale.

[jszymborski]

OK, I thought I was reading too much into it but those same sentences also jumped out for me

[roywiggins]

pangram thinks the whole thing was LLM generated fwiw, as dodgy as AI detectors are it is probably among the best. I don't doubt the author started with their own text, but I think it's been substantially revised via ChatGPT

[DoctorOetker]

yes this reads like classic intellectual fellicitatio