How prevalent are legal hallucinations in AI? Three popular LLMs made big mistakes on a wide range of legal tasks.
LLMS
-
Databricks Adds Mixtral 8x7B Support for Enterprise RAG
By
–
We’re thrilled to announce new support for Mixtral 8x7B in Databricks Model Serving!
— Databricks (@databricks) 16 février 2024
The ability to handle long context lengths + provide faster inference (thanks to MoE architecture) makes Mixtral 8x7B ideal for RAG and other enterprise use cases. https://t.co/HxV2H2k3Ao pic.twitter.com/XzvEhO99pMWe’re thrilled to announce new support for Mixtral 8x7B in Databricks Model Serving! The ability to handle long context lengths + provide faster inference (thanks to MoE architecture) makes Mixtral 8x7B ideal for RAG and other enterprise use cases. https://
bit.ly/3RMbSWa -
CNBC Fast Money: Gemini, ChatGPT4, and Perplexity Comparison
By
–
CNBC Fast Money discussing Gemini, ChatGPT4, and Perplexity (though I actually think they were testing the free version, which is a testament to how even free version of Perplexity can rival paid versions of Gemini/ChatGPT4, and the Paid is superior on research and deep dives).
-
Benchmarks Comparison: GPT-4 and Gemini Ultra
By
–
What’s the benchmarks compared to GPT4 and Gemini ultra?
-
Building Corrective RAG with Open Source Local LLMs
By
–
Building Corrective RAG from scratch w/ open source and fully local LLMs (Video) Building LLM apps with more complex logical flows can be challenging with smaller, local LLMs. Graphs offer one way to tackle this, laying out the logic flow as a graph and using local LLMs for
-
Gemini V1.5 Technical Report Released by DeepMind
By
–
Technical Report: https://
storage.googleapis.com/deepmind-media
/gemini/gemini_v1_5_report.pdf
… -
Prompting Gemini vs ChatGPT: Key Differences Explained
By
–
It’s so interesting how prompting Gemini efficiently is different than ChatGPT and other LLMs. Nice find!
-
RAG-Fusion Query Translation Technique Explained
By
–
RAG From Scratch: Query Translation (RAG-Fusion) Our RAG From Scratch video series walks through impt RAG concepts in short / focused videos w/ code. This is the second in our videos on Query Translation, focused on RAG-Fusion by @Raudaschl
. Problem: A single user -
Gemini Ultra 1.5 API availability coming soon
By
–
Probably because Gemini Ultra 1.5 will ne available very soon so that you’ll reach this via api
-
AI Tool Performs Flawlessly for Coding Tasks Overnight
By
–
It's REALLY good. I was using it for coding all night last night, and it didn't get one thing wrong.