Digital vs biological computing energy costs

Surya Ganguli is quoted in El Reg on the energy cost of fast, reliable, bit flipping. Even with clever hacks, it is expensive.

Biology is completely different. The final answer is just good enough and all the intermediate sets are slow, noisy, and unreliable. But not so unreliable that the final answer isn't just good enough for what's required ... So I think we have to rethink the entire technology stack from electrons to algorithms in order to really go from megawatts to watts.

I couldn’t find a recording of the talk, but there’s a recent podcast covering some of the same ground: From Our Neurons to Yours, 23 May 2024 (from 07:22).

I’d love to learn more about this area. I did pick up a copy of The Energetics of Computing in Life and Machines, but found it too difficulty to get into. I maybe need to give it a good run up.