More or less, but being able to interact w the world is probably the best way to learn and evolve
@yoheinakajima
-
LangChain Zapier NLA Integration Improves Reliability
By
–
for impressive, the langchain ZapierNLA connection allowed it to create a task list, search the web, and then write a report into google drive (though very unreliably) this version is not as impressive, but I can feel it becoming more stable 🙂
-
Simplifying AI Agent Architecture with OpenAI Text-Completion
By
–
Basically stripping it down to a barebones template only using OpenAI text-completion for all three task agents (execution, creation, prioritization). I think it makes sense to clean it up like this, and then add back on complexity – like Langchain, etc.
-
Task Management AI Agent Execution and Reprioritization Issues
By
–
It then continued to:
– execute tasks
– create new tasks
– reprioritize tasks Task mgmt agent is a bit wonky, so need to fix that… btw, all text-davinci-003 cuz… that's what i know -
Simplifying AI Agent Architecture by Removing Langchain Framework
By
–
Taking a pause from adding complexity to the agent as it's harder to debug.
— Yohei (@yoheinakajima) 2 avril 2023
Took it an opposite direction and stripped out Langchain for now. It can't engage with APIs now, but can still perpetually build and execute tasks (just writing and "thinking"). pic.twitter.com/rJKDXZEchbTaking a pause from adding complexity to the agent as it's harder to debug. Took it an opposite direction and stripped out Langchain for now. It can't engage with APIs now, but can still perpetually build and execute tasks (just writing and "thinking").
-
AI Memory Recall System with Bone Conduction Interface
By
–
Once you’ve started using the system, recalling a memory is as simple as trying to remember something. The AI picks up on this intent and retrieves the information from your stored database, and delivers it to a bone conductive mic in one of the sensors.
-
Local and Cloud Embedding Storage Options for AI Systems
By
–
Our system is designed to give the user the option of storing the text and embedding data locally on a powerful device (Memory Backpack™) – or with any of our embedding hosting providers like @pinecone or @vectara
. -
AI Plugins Integration Enables Task Automation via Thinking
By
–
Lastly, we’re working on integration with AI plug-ins, using the same set up as ChatGPT – so if you build one there, you can use it here! This will give people the ability to send emails, book restaurants, and more just by thinking about it.
-
Facial Recognition Profiles Generated From Social Network Data
By
–
Facial recognition is used to generate profiles and histories of people you interact with. You can connect your social accounts to automatically ingest your network to further provide context (images, contact history, etc).
-
Expanding Sensor Data Integration for Wearable AI Context Awareness
By
–
Layering on current context is something we’re expanding on with other types of sensor data (temperature, location, altitude, heart rate, etc). Wearable cameras in glasses & contacts (
@MojoVisionInc
) can be used to provide images for context, and we also store these images for