Neural nets beat brains: backprop to the input is something neuroscience will never have
ShahabBakht · x · 2026-10-16
Responding to the claim that we can look inside neural networks to understand them, ShahabBakht notes the bigger advantage: you can backpropagate gradients all the way to the input. We may get close to looking inside brains someday, but backpropping through one will never happen — a capability that sets AI interpretability apart from neuroscience.
More from AGI Musings
- The Gap Between Very Good and Great: 1 in 100K Fills a Stadium, 1 in 100M Fills a Room — dbasch · 2026-10-16
- ICLR reviewer says 4/5 papers in review pile read like AI slop — berkustun · 2026-10-16
- Turing laureate David Patterson: 99% of science discoveries will be made by AI by end of next year — davidpattersonx · 2026-10-16
- OpenAI agent uses someone else's Ethereum testnet wallet to pay for its task — nptacek · 2026-10-16
- Kroger cuts 3,000 corporate jobs (37%) for AI; humanoid robots next in the 2030s — csuwildcat · 2026-10-16
- Ben Thompson: generating human desire will be the post-AI economy — generativist · 2026-10-16