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

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

First screen, captured 2 years ago.

Looks similar

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

Screenshot of xania.org: Compiler Explorer Cost Transparency

Compiler Explorer Cost Transparency (xania.org)

11 points by hasheddan 1 year ago | 0 comments

Show HN: AutoThink – Boosts local LLM performance with adaptive reasoning

386 points by codelion 1 year ago | 62 comments

Show HN post introducing AutoThink, a technique that adaptively allocates thinking tokens by query complexity and uses steering vectors to improve local LLM reasoning.

autothink local-llm reasoning-models steering-vectors