Phi-3 might even be there already
LLMS
-
Compound AI Systems Outperform Single Models Approach
By
–
Compound AI systems bring models, feedback, external knowledge together; going to be much better than just single models/ single shot approaches!
-
Function Calls as JSON Schema for Multi-Model AI Integration
By
–
Function calls are really just JSON output that fits a specified schema, so definitely possible to use multiple models at the same time by passing JSON strings around
-
Running Small Language Models Locally for RAG and Tool Use
By
–
I'm really excited about the growing potential to run small models on my own laptop (like Llama 3 8B or Phi-3) that don't "know" much but are capable of tool usage and summarization – then I can use them for things like local RAG as well
-
Open Source LLM CLI Tool Reaches 30 Plugins Milestone
By
–
My open source LLM CLI tool just reached 30 plugins! https://
llm.datasette.io/en/stable/plug
ins/directory.html
… -
Benchmark Accuracy vs Real-World Model Performance Analysis
By
–
I think those scores aren't so much general accuracy as they are how many of the increasingly weird challenges in the benchmark the models get right – depending on the application I would expect a model that gets 70% on the benchmarks would get closer to 100% in actual use
-
Function Calling: Underappreciated LLM Application Beyond Knowledge
By
–
Under-appreciated leaderboard in my opinion – function calling (aka tool usage) is one of the most interesting applications of LLMs, plus it should be independent of how much "knowledge" is baked into the models
-
Formalizing LLM Vibes: Toward Empirical Definition and Evaluation
By
–
i'm sure it won't be too long until someone writes a paper claiming to propose a formal definition & evaluation of LLM "vibes"
-
New design of Claude AI with sidebar
By
–
Claude AI is working on "Claudia" – a new page layout with a sidebar. This layout looks much closer to the ChatGPT layout and also hints a link to "Projects IA". The purpose of the "projects" link is yet unclear. Any guesses on what could it be?
-
LLM Updates: Llama 3, Cohere, VoyageAI Embeddings Released
By
–
6/ Enhancement More improvements on other nodes from the community! – UnstructuredIO update
– Llama 3, Cohere on AWS Bedrock
– VoyageAI Embedding
– Custom Dimension OpenAI Embedding
– Confluence PAT support
– many more.. Check out our release page –