Introducing WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting
abs: https://t.co/7aOUxp2sEZ
LLM-based "agents" can interact with external systems by correctly invoking their interfaces, greatly improving over vanilla LLMs.
1/n 🧵
And finally, thanks to my colleagues for supporting this project: @tuicasso, @adamcarrigan, @ZoranPandovski, @vibhuuuus, Daniel Usvyat!
Happy benchmarking!
Introducing WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting
abs: https://t.co/7aOUxp2sEZ
LLM-based "agents" can interact with external systems by correctly invoking their interfaces, greatly improving over vanilla LLMs.
1/n 🧵
P.S.: If you're looking for LLM inference endpoints to try WorkBench out, check out what we're building at @mindshub here: https://t.co/zcb3MJ5HK3
Thanks to the rest of our brilliant co-authors: @bertievidgen @tanayaguha & Victor Sanchez
Integrate modular reasoning of LangChain with autoML magic of MindsDB.
Query data, analyze, retrieve insights, write back responses. Expertly demoed by:
✳️@hwchase17@langchain🦜️🔗 CEO
✳️@paxcema@mindshub Head of ML
📜Code: https://t.co/7aFaMAnJxK
https://t.co/MrVErMHFEw
Join us Wednesday, September 27th, at the SF AI Collective for an evening of discussions around local models, and more!
Featuring:
@jeffreyhuber (Chroma)
@MergenthalerMax (Nixtla)
@mindshub@jmorgan (Ollama)
Invite:
https://t.co/tXpwIa4fWp
Conference day!
I'll be speaking today at #ELCAnnual. We have a really fun panel with @veenormous, @hwchase17, @fede_gr & Rob Ferguson focused on latest developments in the #GenerativeAI space📈
Details: https://t.co/vGvwBUPXZY
Bound for San Francisco 🛫
I'm excited for the @mindshub conference, taking place this Thursday! Among other great sessions, we're teaming up with @hwchase17 to show how you can build domain expert chatbots easily with the Langchain-MindsDB integration.