I have been using it, it’s pretty solid! To me it’s like a GPT-3.8ish. https://t.co/VrZyjsej5w
— Pietro Schirano (@skirano) 12 décembre 2023
I have been using it, it’s pretty solid! To me it’s like a GPT-3.8ish.
LLMS
-
AI Model Review: Comparable to GPT-3.8 Performance
By
–
-
Mistral Medium Advanced Model Limited to Alpha API Access
By
–
Mistral Medium is not on Poe; this is their most advanced model and it's not open-source. It's only in alpha for API users.
-
GPT-4 Hallucinations Impact on App Development Tasks
By
–
GPT-4 is cozily hallucinating a snowy December holiday as you bust in and ask it to build you an app
-
11 Best Practices for Distilling Large Models to Smaller LLMs
By
–
Ready to migrate from #OpenAI to #OpenSource? Check out our 11 best practices for distilling large models like #GPT into smaller, more cost-effective #LLMs. Join our upcoming webinar to get them all! See you there! https://
pbase.ai/3todbm1 -
Benchmarking AI Models with December 25 Date Input
By
–
Did anyone do benchmarks on telling it the date is Dec 25?
-
Med-PaLM: High-Quality Medical Question Answering LLM
By
–
Med-PaLM is an #LLM designed to provide high quality answers to medical questions. Learn all about it today at 4:45pm, when Tao Tu will be at the #NeurIPS2023 Google to discuss Med-PaLM's capabilities. pic.twitter.com/FnTzxBW6kF
— Google AI (@GoogleAI) 12 décembre 2023Med-PaLM is an #LLM designed to provide high quality answers to medical questions. Learn all about it today at 4:45pm, when Tao Tu will be at the #NeurIPS2023 Google to discuss Med-PaLM's capabilities.
-
NeurIPS Tutorial: Building AI Applications with Large Language Models
By
–
At the NeurIPS tutorial that @isafulf and I presented on Application Development using LLMs, it was great to see the enthusiasm for all the new AI apps now possible. Thanks also to @anbarth @tatsu_hashimoto @merrierm @gneubig for being on our panel, and to everyone that came!
-
ToolBench: Evaluating LLM-Based API Agent Performance
By
–
Agent-based manipulation of APIs using #LLMs is a popular approach, but consistent and reliable evaluation metrics to assess this has been lacking. In this poster, we introduce a set of benchmarks called ToolBench and evaluate multiple open source #LLMs. @SambaNovaAI Researcher
-
Google Gemini Model Presentation at NeurIPS 2023
By
–
Want to learn more about the new Google Gemini model? Join Jeff Dean and members of the Gemini team at the #NeurIPS2023 Google booths today at 1:30pm to hear all about it!