DYoshida
Article
DYoshida is a recurring person in the Astral Codex Ten archive, appearing 2 times across 2 issues between August 06, 2021 and December 04, 2023. The archive places it in contexts such as “DYoshida writes : This isn’t directly related to the article”; “dyoshida on simulation”. It most often appears alongside accelerationists, ACX, AGI.
Metadata
- Category: People
- Mention count: 2
- Issue count: 2
- First seen: August 06, 2021
- Last seen: December 04, 2023
Appears In
Related Pages
-
- accelerationists (1 shared issues)
-
- ACX (1 shared issues)
-
- AGI (1 shared issues)
-
- AI (1 shared issues)
-
- AI Impacts (1 shared issues)
-
- AI risk (1 shared issues)
-
- algorithmic bias (1 shared issues)
-
- alignment (1 shared issues)
-
- AlphaGo (1 shared issues)
-
- AlphaZero (1 shared issues)
-
- AlphaZero (1 shared issues)
-
- basilisks (1 shared issues)
External Links
Source Context
Recovered passages from the original issue text. When the raw archive preserved outbound links inside the source passage, they are listed directly under the quote.
1: Some good comments on the monosemanticity post, including dyoshida on simulation, johnny_lin’s attempt to gamify explaining AI, theahura on the analogy to polygenicity, sclmlw on cell signaling pathways, bestgreatestsuper on manifolds. And Benji York links a post on 11-dimensional abstract structures in the human brain. Many of these seem to be getting at the same idea where there are evolved systems scientists have so far failed to really understand - AIs, the genome, cellular signaling pathways - and maybe the same idea of a polysemantic → monosemantic reduction will help with all of them. I would love to see a longer treatment of this by someone who knows what they’re talking about.