152334h.github.io on Hacker News

2 stories on the front page, newest first. Scroll down to watch the site change over time.

Screenshot of 152334h.github.io: Calculating the cost of a Google DeepMind paper

Calculating the cost of a Google DeepMind paper (152334h.github.io)

270 points by 152334H 2 years ago | 134 comments

Screenshot of 152334h.github.io: Non-determinism in GPT-4 is caused by Sparse MoE

Non-determinism in GPT-4 is caused by Sparse MoE (152334h.github.io)

360 points by 152334H 3 years ago | 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.

gpt-4 mixture-of-experts non-determinism openai

152334h.github.io on Hacker News

Calculating the cost of a Google DeepMind paper(152334h.github.io)

Non-determinism in GPT-4 is caused by Sparse MoE(152334h.github.io)

Calculating the cost of a Google DeepMind paper (152334h.github.io)

Non-determinism in GPT-4 is caused by Sparse MoE (152334h.github.io)