AGENTS - AI Dynamics

Online RL agents make interventions with a goal. I believe this is enough, but I’d like to hear @eliasbareinboim expanding on this as I believe he’s put a lot of thought into it. I also think multimodality helps, based on the rubber hand illusion, e.g. @anilkseth

→ View original post on X — @nandodf

16 January 2023

Chatbots Lack Causal Reasoning and Agency: Solutions Needed

By

@nandodf

–

16 January 2023 22h08

Existing chatbots are not causal reasoners. They lack agency. They treat their actions (what they said) as observations and not as interventions. Question: how do we fix this? @yudapearl I think there’s a few solutions, but I’d love to hear you thoughts. @eliasbareinboim

→ View original post on X — @nandodf

16 January 2023

Agent Response Parsing Improvement for Final Answers

By

@langchain

–

16 January 2023 16h58

Parsing of agent responses – h/t @krrish_dh Previously, the agent response expected the "final answer" to start on the same line as the "Final Answer" prefix. For longer answers, this sometimes didn't happen We now longer enforce that it be on the same line

→ View original post on X — @langchain

16 January 2023

Version 0.0.64 Release: Enhanced Robustness for Large Context

By

@langchain

–

16 January 2023 16h58

v0.0.64 a bunch of updates making it more robust to large context Updated API chain – @fpingham Updated SQL chain – @fpingham New multistep SQL chain
Parsing of agent responses – h/t @krrish_dh and Wikipedia source information – @rubensmau

→ View original post on X — @langchain

16 January 2023

Blubi AI: Build Chatbots on Your Content Tool

By

@futurepedia_io

–

16 January 2023 5h04

came across a cool tool that would enable you to build chatbots on top of your content check it out – https://
futurepedia.io/tool/blubi-ai
cc @5harath

→ View original post on X — @futurepedia_io

16 January 2023