Post

In my quest to understand the true nature of an Agent I have been thinking a lot about the loop and the actions and the environment. And I think i see where we're headed next. Agents are not going to be like chatbots. They are going to be like programming languages come alive.

Right now most people's working definition of an agent is "a language model in a loop with some tools", right? This is the ReAct paradigm. The models are trained around it, from data formatting to inference stack. Tool calling, function calling, MCPs all rely on this turn-by-turn structure.

But context is still the bottleneck, and all the tool call inputs and outputs still have to go through the input. In the meantime we had things like CodeAct, and Code Mode, and Claude Code, that give the model access to some kind of REPL

(Read Eval Print Loop, an interactive computational environment, like a terminal or a programming language notebook). And we’ve seen models simulate computer environments as well, like in worldsim and Infinite Backrooms.

when those surfaced I also believed that agentic workflows would mostly take such forms, mainly something akin to 100r.co/site/paradis... as a way to shape the environment as a “ghost haunting contextual objects”. Anything on that direction that you know of?

It was the idea a “ghost” becoming, and transforming the/into elements in its environment, and always thought agentic first systems should follow it. If in the infinite back rooms their ability to “become” was so prominent, why are agents just “automated users”? When such abstractions are possible

As you control the ghost in Paradise, you could control the agent, not in a way where you would “talk to it” but channel it across your contextual environment