LLMS

LLMs Long Context Windows Reduce Data Preparation Needs

By

–

13 July 2023 21h28

This is a perfect application of LLMs with long context windows The longer the context window, the less time you have spend beforehand clustering/preparing the data Sign up for the @AnthropicAI hackathon (we'll be there!) to try out things like this! https://
x.com/AnthropicAI/st
atus/1679494670047379456?s=20
…

→ View original post on X — @jeande_d

GPT-4 Performance Expectations vs Reality: The Adaptation Effect

By

@jeande_d

–

13 July 2023 20h34

Anyone thinking the performance of GPT-4 may have degraded, it probably didn’t. As we get used to AI systems, our expectations increases(this is true for any new technology that is still finding its ways, remarkable example is uncanny valley in robotics). The key to working with

Analyzing Natural Language Interactions with LLMs

By

–

13 July 2023 19h26

Analyzing natural language interactions with LLMs The new interface for apps is through natural language. This means there is a new category of user interactions to analyze And the best way to analyze natural language interactions is… with an LLM

Automatic Metadata Extraction Using LLMs Now Available

By

–

13 July 2023 17h51

Automatic Metadata Extraction @RLanceMartin has done a lot of work showing how having the correct metadata attached to documents can be valuable, but there's still the question: how do you get that metadata? Use an LLM to extract it of course! Now live in JS and Python

LangChain Integrates Context AI for Chat Analytics

By

–

13 July 2023 17h10

Chat Application Analytics Introducing an integration with @getcontextai which allows you to receive user analytics with a one line plugin Blog: https://
blog.langchain.dev/langchain-x-co
ntext-building-better-chat-products-with-user-analytics/
… Integration: https://
integrations.langchain.com/callbacks?inte
gration_name=ContextCallbackHandler
…

→ View original post on X — @honnibal

Release of curated-transformers: Pure PyTorch library for LLMs

By

@honnibal

–

13 July 2023 16h24

Excited to release this! A pure @PyTorch library for LLMs and other transformers. It strikes a different trade-off from @huggingface Transformers. curated-transformers won't be up-to-the-minute with new architectures, added verbatim. Instead the implementations are factored out https://
x.com/spacy_io/statu
/spacy_io/status/1679480083801866241
…

→ View original post on X — @groqinc

CEO Jonathan Ross Discusses LLMs Live Today

By

@groqinc

–

13 July 2023 16h15

Today we're talking #LLMs with our CEO & Founder, @JonathanRoss321
. Join us at 11am PST on LinkedIn or YouTube live to be part of the conversation.

→ View original post on X — @anthropicai

Claude 2 Launch: Anthropic Partners With Leading AI Ecosystem

By

@anthropicai

–

13 July 2023 16h15

Thanks to our partners @cerebral_valley and @iendeavors
, and supporters @llama_index
, @langchain
, @huggingface and @arizeai
. We can’t wait to see what you build with Claude 2!

→ View original post on X — @cohere

Chrome Extension for Web Page Summarization Using LLMs

By

@cohere

–

13 July 2023 16h13

Large language models enable new classes of applications to enrich the web browsing experience. A key use case is summarization. This tutorial demonstrates how to create a Google Chrome extension that summarizes a web page using the Summarize endpoint. https://
short.cohere.ai/EQ9HPS