TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Show HN: Mockingbird is an LLM that outperforms GPT4 on RAG

9 pointsby eskibars10 months ago
Hi HN!<p>I lead product at Vectara and we&#x27;ve just released a new LLM in our platform that outperforms GPT4 and Gemini 1.5 Pro on RAG tasks.<p>Vectara is a Retrieval Augmented Generation (RAG) platform primarily deployed as a SaaS service which includes a generous free tier so you can try it for free.<p>The way we&#x27;ve been able to offer a &quot;better but cheaper&quot; is that we focus a lot of our attention on taking smaller models (which can be hosted in a cost efficient way) and fine tuning them to specific tasks: in this case RAG. This ends up with a model that is <i>less</i> capable of arbitrary tasks like crafting creative stories, but for many enterprises we&#x27;ve learned they don&#x27;t see the &quot;creativity&quot; of LLMs as a positive, as they also result in hallucinations.<p>Would love feedback!

1 comment

llm-apprentice10 months ago
I think we all recognize that specialized models are the future. Great to see Vectara already on that path for RAG (enterprises)!