5/ Unfaithful Explanations in Chain-of-Thought Prompting – demonstrates that CoT explanations can misrepresent the true reason for a model’s prediction.
LLMS
-
ChatGPT Speeds Up SQL Query Writing Process
By
–
I'm not an expert in SQL and writing a query like this one would have taken me a lot of time (visiting multiple websites, several query attempts, finding right search term, etc). But with ChatGPT, it took me just two prompts and ~1 min ¯_(ツ)_/¯
-
Creating AI Personalities with Embeddings from Content
By
–
Personalities were generated with very simple starter prompts, and we baked tweets and old podcasts/content in through vector embeddings to make these folks who they are.
-
GPT-4 Advances Knowledge Work Across Strategic Creative Domains
By
–
GPT-4, and other advanced generative AI tech, has accelerated the ability of AI to perform knowledge work (including strategic and creative work) in ways we’re still exploring and trying to understand. https://
youtu.be/D_ZpLaFV_ZE -
LangChain Webinar: LLMs Transforming Education and EdTech
By
–
Giving a 2+ weeks heads up for a VERY exciting @langchain webinar: LangChain in Education – how LLMs and LangChain are changing education and educational technology. https://
crowdcast.io/c/q5y8g08f1f74 We’re excited for a slate of engaging speakers, including: -
FLARE: Forward-Looking Active Retrieval Augmented Generation Method
By
–
FLARE Forward-Looking Active REtrieval augmented generation A new retrieval augmented generation method from Zhengbao Jiang, @luyu_gao et all Now in @langchain – slightly modified to support using http://
serper.dev as the retriever https://
python.langchain.com/en/latest/modu
les/chains/examples/flare.html
… -
FLARE Paper: Active Learning for Language Models
By
–
Original paper: https://
arxiv.org/abs/2305.06983
code
…: https://
github.com/jzbjyb/FLARE Original code: http://
github.com/jzbjyb/FLARE Some good tweet threads explaining more: @omarsar0 https://
x.com/omarsar0/statu
s/1657004417726423042?s=20
… @johnjnay -
Repository Integration with LangChain Framework
By
–
your repo is awesome. would love to chat about how to make sure it works well with langchain. can you shoot me a dm? yours dont seem to be open
-
PrivateGPT Enables Open Source Models with LangChain Integration
By
–
privateGPT – this is sick!!! I've always had people asking me if it was feasible to use @langchain with open source models, and my answer was "at the moment, not really…" but @ivanmartit did it!!!!! this is a huge step forward
-
Anthropic Launches Longest Consumer AI Context Window
By
–
Thanks to Anthropic’s innovation, this is the longest context window available in any consumer product, and we are excited to see what everyone does with it! We are working on enabling file uploads and mobile app support for this bot as a next step. https://t.co/XWZje7QQJB
— Poe (@poe_platform) 13 mai 2023Thanks to Anthropic’s innovation, this is the longest context window available in any consumer product, and we are excited to see what everyone does with it! We are working on enabling file uploads and mobile app support for this bot as a next step.