Conversation will be the new interface. On the latest episode of @WIRED
's Have a Nice Future podcast, our CEO @mustafasuleyman joins @LaurenGoode and @glichfield to discuss the future of personal AI and what to expect from new technologies:
AGENTS
-
Conversation as the New Interface for Personal AI
By
–
-
LLMs for Structured Data Extraction and Web Automation
By
–
An underrated aspect of LLMs is using them for structured data extraction Extracting knowledge triplets is a great use case! I gave it our most recent blog post about @MultiON_AI (
https://
blog.langchain.dev/multion-x-lang
chain-powering-next-gen-web-automation-navigation-with-ai/
…) and it came up with the below – how did it do @DivGarg9 ?? -
ChatLangChain Improvements: Benchmarking Retrieval and Agent Methods
By
–
ChatLangChain Improvements We're benchmarking a bunch of retrieval and agent methods for our "chat langchain" app! Interact with the new beta version here: …
https://chat-
langchain-mcan-stanfordedu.vercel.app Expect rapid improvements and everything (data, retrieval algorithms, prompts) to be OSS -
Google Tests AI Assistant Offering Life Advice
By
–
Google Tests an #AI Assistant That Offers Life Advice https://
nytimes.com/2023/08/16/tec
hnology/google-ai-life-advice.html?smid=tw-share
… -
System Message Optimization for AI Function Agents
By
–
i would probably tell it explicitly in the system message what you just wrote – "if you do not find a person in the prof, search in founder" or someting also would use OPENAI_FUNCTIONS agent
-
Cohere LLMs Powering Productivity Meetup Toronto London
By
–
Hey Toronto and London UK folks! Join us for the ultimate gathering of the summer at our Cohere offices for our LLMs Powering Productivity Meetups! Ever thought of crafting your own knowledge agent? Learn how Cohere and LangChain-powered LLMs can help redefine your app and
-
Meta AI Introduces Shepherd: A Model for Critiquing and Refining Responses
By
–
New research from Meta AI — Shepherd is a language model specifically tuned to critique model responses & suggest refinements. It goes beyond the capabilities of untuned models to identify diverse errors & suggest improvements. Read the paper https://
bit.ly/3QC4AW3 -
SQL-LangChain App: LLM-Powered Database Querying Tool
By
–
Access the app here: https://
sql-langchain.streamlit.app Please leave feedback on questions that the current implementation does a particularly good or bad job at answering! If you want to see the underlying code, its at this repo: https://
github.com/hwchase17/sql-
qa
… -
Local Models Power Generative Agents Fork Cost Reduction
By
–
Forks of generative agents repo hooked up to local models!!! Keeps costs down but fun up
-
Microsoft Builds Personal AI Pi on Azure Infrastructure
By
–
Read more about our work to build out Pi – your personal AI – on Microsoft Azure's world class AI infra Thanks for the great partnership @kevin_scott and @MParakhin