📢Excited to release GoEx⚡️a runtime for LLM-generated actions like code, API calls, and more. Featuring "post-facto validation" for assessing LLM actions after execution 🔍 Key to our approach is "undo" 🔄 and "damage confinement" abstractions to manage unintended actions & risks. This paves the way for fully autonomous LLM... agents, enhancing interaction between apps & services with human-out-of-loop🚀 Blog: Code: Paper:show more

🌐 Pioneering a future where LLMs empower microservices & apps, evolving from mere data retrievers 🧵to autonomous decision-makers within our digital world 🧙 Wondering about the safety and correctness of these interactions🤔? Our latest vision paper explores these questions, laying out design principles for the next-step in LLM powered applications 💯

We study the inherent challenges in relying on LLMs—addressing their unpredictability, the essential trust mechanisms for their decision-making, and hurdles in failure recognition & resolution. Our system, GoEx presents abstractions and policies to overcome these for RESTful APIs, and operations on databases and filesystems! An exhilarating collaboration with @tianjun_zhang @vivianfxng Noppapon C @_royh021 Aaron Hao @profjoeyg @ralucaadapopa Ion Stoica from @UCBerkeley and @martin_casado from @a16z

in your API inventory, what % had an undo function?

@vivianfxng hi

cc @ibuildthecloud

I read your paper and it's the first time I see this approach. Based on the code, you just define a "reverse tool" for each tool the LLM can use, is it correct? For the types of actions you cannot reverse, I suggest running the LLM output in a safe sandboxed environment, e.g. using the @e2b_dev Code Interpreter SDK: There, the actions that the LLM agent "decides" to do are isolated in a separate sandbox instance.