Kimi K3, and what we can still learn from the pelican benchmark
https://simonwillison.net/2026/Jul/16/kimi-k3/loading story #48952923
loading story #48949188
loading story #48956159
loading story #48950515
loading story #48960409
loading story #48949300
loading story #48955087
loading story #48950886
loading story #48952755
loading story #48951738
loading story #48950284
loading story #48950134
loading story #48959418
loading story #48950116
loading story #48952202
loading story #48949960
loading story #48949739
loading story #48950616
loading story #48955679
loading story #48950749
loading story #48950278
loading story #48949461
loading story #48956572
loading story #48949239
loading story #48949164
Another day, another model and another pelican :-)
I can't help but wonder where is the trend going? What will we have in five years? Maybe it will all have puttered out, and we will have moved to the next thing? Or maybe the prompt then will be "make a pelican ride a bicycle", and out will come the genetic code for a giant pelican with extremities suitable for a handle bar and pedals, and an inborn affinity to ride bicycles?
loading story #48949079
You are thinking too hard on this. This entire "benchmark" is a performative joke for attention that only works on HN.
> What will we have in five years? Maybe it will all have puttered out, and we will have moved to the next thing?
We will just have more of the same.
loading story #48950752
loading story #48949591
loading story #48951055
loading story #48955972
loading story #48955899
loading story #48949457
loading story #48949856
loading story #48953667
loading story #48952798
loading story #48957801
loading story #48956850
loading story #48956506
loading story #48956101
loading story #48952156
loading story #48958175
loading story #48954919
loading story #48959270
loading story #48949008
loading story #48949759
loading story #48950802
loading story #48949556
loading story #48949257
loading story #48957066