Foundation models took center stage in 2023. We created this explainer for non-experts: @StanfordCRFM
LLMS
-
LLM Tool Use Benchmarking: OpenAI Claude Mixtral Mistral
By
–
Which LLMs are best at using tools? OpenAI > Claude > Mixtral > Mistral Which others ones should we benchmark?
-
Anthropic Messages API and Claude 2.1 Integration with LangChain
By
–
Anthropic Messages Use Anthropic’s new beta Messages API and Claude 2.1 with the new
@langchain x @AnthropicAI packages in Python and JS! With better support for processing your Chat Messages in the correct format, give ChatAnthropicMessages a go! -
v1.4.7 Release: Gemini, MistralAI, If-Else Branching
By
–
Latest release – v1.4.7 before Google Gemini MistralAI If Else Branching Custom JS Function Conversation Starters Logo revamp
-
Google Gemini and MistralAI Now Available as Embeddings Chat
By
–
Google Gemini + MistralAI Now available as embeddings + chat models:
-
Build Bots with GPT-4, Claude 2, DALL-E 3, SDXL on Poe
By
–
You can build your bot on top of LLMs like GPT-4, Claude 2, DALL-E 3, and SDXL, customize it with a knowledge base, and reach a worldwide audience of millions. Visit http://
poe.com/creators to join! (3/3) -
Google Bard Gets Gemini Pro Update, Free to Use
By
–
10. Bard (Gemini Pro update)
— The Rundown AI (@TheRundownAI) 20 décembre 2023
Google's new model (Gemini Pro) integrated directly into Bard.
Huge update to Bard, and completely free to try.
Link: https://t.co/755CdKiyV9pic.twitter.com/Va7ZCw0xgY10. Bard (Gemini Pro update) Google's new model (Gemini Pro) integrated directly into Bard. Huge update to Bard, and completely free to try. Link: https://
bard.google.com -
Testing LLM Agents: Benchmarking Guide and Performance Evaluation
By
–
11/ Test your own agent Want to test out a new LLM? Agent architecture? Prompting strategy? Run these benchmarks on your own agent by following this easy guide: https://
langchain-ai.github.io/langchain-benc
hmarks/notebooks/tool_usage/intro.html
… Performance is a function of the whole system. We were only able to clearly run a small -
Typewriter Task: Agent with 26 Letter Tools
By
–
4/ Task 2: Typewriter (26 tools) Agent has 26 tools, 1 for each English letter. It has to type the provided word. https://
langchain-ai.github.io/langchain-benc
hmarks/notebooks/tool_usage/typewriter_26.html
…