Looks similar
Sampling with SQL(blog.moertel.com)
162 points by thunderbong | 36 comments
Entropy of a Mixture(cgad.ski)
45 points by cgadski | 4 comments
The Ken Thompson Hack(wiki.c2.com)
98 points by stephc_int13 | 27 comments
Non-determinism in GPT-4 is caused by Sparse MoE(152334h.github.io)
360 points by 152334H | 162 comments
Blog post arguing that GPT-4's non-deterministic outputs at temperature zero are caused by its sparse mixture-of-experts architecture and batched routing.






