LLMS

Hard stuff when building products with LLMs
246 points | 109 comments

Chain-of-Thought Hub: Measuring LLMs' Reasoning Performance
114 points | 26 comments

Voyager: An Open-Ended Embodied Agent with LLMs
94 points | 25 comments

Anyscale's Aviary is a dashboard for evaluating Open Source LLMs
14 points | 3 comments

Show HN: Generate Swift unit tests using LLMs
14 points | 0 comments

Ask HN: What can we learn about human cognition from the performance of LLMs
11 points | 3 comments

Aviary: Compare Open Source LLMs for cost, latency and quality
6 points | 0 comments