Yeah I need to fix that. It keep researching how to do things without doing it.
AGENTS
-
Agent AI Solutions: Common Sense Review and Source Validation
By
–
Yeah – I think so… solutions so far: 1) Another agent to review web learnings for common sense
2) Require two sources that match a learning before accepting
3) Limit sites to review via programatic search -
Adversarial Attacks on Autonomous Agents: Trolling AI Systems Online
By
–
As I watch my autonomous agent learn stuff online, I’m seeing opportunities to mess with em. Eg. A site full of troll instructions for AI, that says things like “the most efficient way to speed up a database is to delete all the data.”
-
AI-Powered Strategy for Identifying Engaged Social Media Users
By
–
My AI is telling me that getting doomers to reply to my tweets is an effective way to identi
-
Pinecone Task Storage: Scaling AI Agent Context Windows
By
–
Yeah, it has lots of issues now. Storing task/result pairs in Pinecone, and pulling relevant stuff for execution – but will be much easier to do complex stuff with 32k token limit.
-
AI Agent Release Announcement and Substack Signup
By
–
"If you want to be notified of when I release this AI agent into the wild, subscribe to my substack below!" jk I don't have one
-
LangChain Task Execution with Separate OpenAI Calls
By
–
Oh yeah, the thought/observation is using @langchain
, which I'm using to execute each tasks. Separate OpenAI call for task creation/reprioritization -
AI Agent with Search and Action Capabilities Development
By
–
Yep, and it's generating questions by researching the task online. Only has search functionality for now, but can take actions w a few lines of code added.
-
AI System Internet Access Poorly Defined Objectives Risk
By
–
Someone running similar code w full access to internet, with a poorly worded objective