Diff of Good Ideas at 5795872

@@ -103,2 +103,4 @@ Semantic search for:
 * Improve AI-based search with methods other than making boring contrastive embedding models very slightly better.
-* Graph-based vector indices do beam search on a graph constructed so that beam search on dot product or PQ dot product "mostly" returns the closest (highest-dot-product) result. Do one of several RL/etc pathfinding schemes instead (like https://arxiv.org/abs/2502.18663)? We only have a budget of 100μs per read node, though, so this is a bit tricky.
\ No newline at end of file
+* Graph-based vector indices do beam search on a graph constructed so that beam search on dot product or PQ dot product "mostly" returns the closest (highest-dot-product) result. Do one of several RL/etc pathfinding schemes instead (like https://arxiv.org/abs/2502.18663)? We only have a budget of 100μs per read node, though, so this is a bit tricky.
+* SAEs/dictionary learning algorithms for residual quantization.
+* Minecraft/Factorio crossover modpack via Clusterio-like thing.
\ No newline at end of file