we are working to improve the default settings to be more neutral, and also to empower users to get our systems to behave in accordance with their individual preferences within broad bounds. this is harder than it sounds and will take us some time to get right.
AGENTS
-
Blind AI Agents Learn Navigation Through Emergent Neural Representations
By
–
We train blind AI agents to navigate — i.e. no sensory input other than ego-motion and found the emergence of wall-following, collision-detection neurons, and map-like representations in their memories. This provides new insights into the success of 'map-free' navigation agents.
-
Blind Navigation Agents Learn to Create Mental Maps
By
–
📣 New paper: Emergence of Maps in the Memories of Blind Navigation Agents
— AI at Meta (@AIatMeta) 1 février 2023
Humans have the ability to navigate poorly lit spaces by relying on touch and memory. Our research shows that blind AI agents can learn to do the same.
Read the paper ➡️ https://t.co/XY5kNU5FwR pic.twitter.com/IbfumhR4ZUNew paper: Emergence of Maps in the Memories of Blind Navigation Agents Humans have the ability to navigate poorly lit spaces by relying on touch and memory. Our research shows that blind AI agents can learn to do the same. Read the paper https://
bit.ly/40evpCh -
Minedojo Featured in Foundation Models for Decision Making Article
By
–
Thank you @laxmevy for featuring Minedojo in an in-depth article on using pre-trained foundation models for decision making
-
GPTwitter: Novel User-Level Personalization on LangChain
By
–
Introducing the first of hopefully many guest posts highlighting novel applications building on top of LangChain GPTwitter: an application that we believe achieves user-level personalization in a novel, reproducible, and under-explored way
-
AR Glasses and Robots: Exponential Value Through AI Integration
By
–
it will be the combination of the categories that is the most interesting the value of AR glasses increases exponentially when you integrate an AI assistant within it, same with the robot
-
Cohere AI Wrappers Updates and Conversational Agent Fixes
By
–
And others! Updates to @CohereAI wrappers There were a few updates/fixes to the Cohere wrappers from @ephe_meral and @bair82 Fix to conversational agent
Docs update @zurawiki Expose memory key name in entity memory class -
Enhanced Agent Initialization with Advanced Parameters
By
–
More complete initialization of agents Thanks to @jxnlco you can now more completely initialize agents by specifying `agent_kwargs` This allows for passing of more complex parameters to the agent class https://
github.com/hwchase17/lang
chain/blob/b9045f7e0df357d608700e91dc3039433f652d61/langchain/agents/initialize.py#L17
… -
LangChain v0.0.75 Release: Agents, Embeddings, SQL Steps
By
–
Another big release! v0.0.75 Pin LangChainHub version (
@roywilliamsiii
)
TensorflowHub embeddings (Ryohei Kuroki)
Returning intermediate SQL steps
Better initialization of agents (
@jxnlco
)
Using MMR search in the vector DB QA chain And more! -
LangChainHub Now Supports Git Commit Version Pinning
By
–
Pin LangChainHub version Thanks to @roywilliamsiii you can now load artifacts from LangChainHub from a specific git commit, effectively pinning the version Docs: https://
langchain.readthedocs.io/en/latest/modu
les/agents/examples/load_from_hub.html#pinning-dependencies
… Check out the Hub here: