Top all-time · #24921
goddard.blog
Personal blog · goddard.blog/postsaiwriting
goddard.blog is a personal blog at goddard.blog about ai and writing. Since 2024, 3 different Hacker News readers have linked it 3 times, most often “Mixture of Experts for Clowns (At a Circus)”. No feed was found, so read it on the site itself.
Too few sampled comments (1) to say how often HN recommends it.?
Why HN links it
HN readers link this blog as the work of the mergekit developer, covering LLM model merging. One commenter calls the developer's blog great and links it.
Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Most-linked posts?
- Mixture of Experts for Clowns (At a Circus)2 people · 2 mentions · first linked 2024-01-03
What Hacker News says?
Mergekit is the best thing since sliced bread, as the local llm community already knows. The dev's blog is great: https://goddard.blog/posts/ ...But its not what this paper is describing. They are basically alternating models, AFAIK. Also I have other nitpicks with the paper, like using extremely old/mediocre chat models as bases: > Pygmillion 6B, Vicuna 13B, Chai Model 6B
Comment linking /posts/
on “Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM”Submitted Mixture of Experts for Clowns (At a Circus) as a story · 2 points
HN discussionSubmitted Mixture of Experts for Clowns (At a Circus) as a story · 1 points
HN discussion