Re:Anthropic's original take home assignment open sourced
by lalaland1125 on Wednesday January 21, 2026 @01:23PM
(#46709454)
How do you avoid the load bottleneck?
[ Parent
| on HN ]
Re:Anthropic's original take home assignment open sourced
by amirhirsch on Wednesday January 21, 2026 @01:31PM
(#46709546)
take advantage of index collisions, optimizing round 0 and 11, speculative pre-loading, and the early branch predictor (which now I am doing looking at bits output at stage 3)
Re:Anthropic's original take home assignment open sourced
by lzhou on Wednesday January 21, 2026 @04:35PM
(#46711895)
it's actually pretty funny since opus will suggest both of these with enough prying (though with a single-prompt it might not try it).
Re:Anthropic's original take home assignment open sourced
by amirhirsch on Wednesday January 21, 2026 @04:25PM
(#46711772)
======================================================================
BROADCAST LOAD SCHEDULE
======================================================================
Round | Unique | Load Strategy
------|--------|------------------------------------------
0 | 1 | 1 broadcast → all 256 items
1 | 2 | 2 broadcasts → groups
2 | 4 | 4 broadcasts → groups
3 | 8 | 8 broadcasts → groups
4 | 16 | 16 broadcasts → groups
5 | 32 | 32 broadcasts → groups
6 | 63 | 63 loads (sparse, use indirection)
7 | 108 | 108 loads (sparse, use indirection)
8 | 159 | 159 loads (sparse, use indirection)
9 | 191 | 191 loads (sparse, use indirection)
10 | 224 | 224 loads (sparse, use indirection)
11 | 1 | 1 broadcast → all 256 items
12 | 2 | 2 broadcasts → groups
13 | 4 | 4 broadcasts → groups
14 | 8 | 8 broadcasts → groups
15 | 16 | 16 broadcasts → groups
Total loads with grouping: 839Total loads naive: 4096
Load reduction: 4.9x