Have You Tried Thinking About It As Crystals? — LessWrong
Epistemic Status: Written with my Simulator Worlds framing. E.g I ran simulated scenarios with claude in order to generate good cognitive basins and then directed those to output this. This post is Internally Verified (e.g I think most of the claims are correct with an average of 60-75% certainty) and a mixture of an exploratory and analytical world.[1] This post also has a more technical companion piece pointing out the connections to Singular Learning Theory and Geometric Deep Learning for the more technically inclined of you called Crystals in NNs: Technical Companion Piece. Scene: A house party somewhere in the Bay Area. The kind where half the conversations are about AI timelines and the other half are about whether you can get good pho in Berkeley. Someone corners an interpretability researcher near the kombucha. (Original story concept by yours truly.) CRYSTAL GUY: So I've been thinking about shard theory. INTERP RESEARCHER: Oh yeah? What about it? CRYSTAL GUY: Well, it describe
x Have You Tried Thinking About It As Crystals? — LessWrong Shard Theory AI Frontpage 77 Have You Tried Thinking About It As Crystals? by Jonas Hallgren 28th Dec 2025 13 min read 12 77 Epistemic Status: Written with my Simulator Worlds framing. E.g I ran simulated scenarios with claude in order to generate good cognitive basins and then directed those to output this. This post is Internally Verified (e.g I think most of the claims are correct with an average of 60-75% certainty) and a mixture of an exploratory and analytical world. [1] This post also has a more technical companion piece pointi
saved by
related reading
- Crystals in NNs: Technical Companion Piece — LessWronglesswrong.com
- Simulators — LessWronglesswrong.com
- LessWronglesswrong.com
- Please don't throw your mind away — LessWronglesswrong.com
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- The shard theory of human values — LessWronglesswrong.com
- Maybe I was too harsh on deep learning theory (three days ago) — LessWronglesswrong.com
- As Rocks May Think | Eric Jangevjang.com
- Why I'm bearish on mechanistic interpretability: the shards are not in the network — LessWronglesswrong.com
- interpreting GPT: the logit lens — LessWronglesswrong.com
- A Three-Layer Model of LLM Psychology — LessWronglesswrong.com
- How An Algorithm Feels From Inside — LessWronglesswrong.com