Embra was one of the first AI Agents startups. Today, we are...

Embra was one of the first AI Agents startups. Today, we are renaming AI Agents to AI Commands, and narrowing our focus away from autonomous agents. While autonomous agents took off in popularity, we found they were often unreliable for work, inefficient, and unsafe. 🧵

Zach Tratar

twitter.com

Saved by Darren LI

RelatedHighlightsCollections

This has some problems: - Failure rate is high - Even when successful, they're often costly + inefficient - Full autonomy removes humans from being in control (!) - Agentic controls are weak - Security concerns are very real. Autonomy + access to your private data =

Zach Tratar • Tweet

Professionals should be the ones making the important decisions and steering AI, not letting it run loose hoping for the best.

Zach Tratar • Tweet

but the question is how?

But regular end-users, even engineers, cannot assess safety based on model weights. And prompt injection remains a large attack vector.

Zach Tratar • Tweet

First off, a primer on autonomous agents: - Give them a task - Give them memory - Give them access to tools - They decide on-the-fly how to accomplish your task and remove you from this process because... it's autonomous - Watch them attempt to do the work

Zach Tratar • Tweet

Agents are arms and legs of LLMs