ClaimAudio · 69:37 — 71:07
MCP and traditional tool calls are 'stupid' — the future is models writing code freely in a minimal container, not choosing from 50 predefined tools in a system prompt.
Eiso argues that stuffing 50 tools into a system prompt is the wrong direction. Instead, models should be given a minimal harness with a container, codebase, and API keys, and allowed to write scripts with if-statements and loops to solve complex tasks. He predicts this will be the norm within 12 months. ✦ AI generated
Eiso Kant · Latent Space · 2026-07-23 · original ↗
plays this moment only · 69:37 — 71:07
I think MCP and tools are stupid... we are moving from tool calls to effectively models writing code, little scripts... Give the model a minimal harness, as minimal as possible, give it a container in which it has its own code base... and just let it run free at the task. And I think that is the way we're going.
verbatim transcript · starts at 69:37
Transcript · around this moment
69:26Why MCP and Traditional Tool Calls Are “Stupid”
Around this claim
Counterpoint · 2
Giving an agent a shell environment with internet access is fraught with risk and requires a strong driving model, whereas MCP tools are easier to audit and control and are simple enough that smaller laptop models can drive them, and the stateless spec greatly cuts client and server implementation complexity.Simon Willison · Simon Willison's Weblog · conf 75%Even though MCP has its own prompt injection security problems, arbitrary shell and curl access in an open network environment is much harder to keep secure, and MCP makes it easier to reason about agent capabilities and failure modes — which is why I plan to lean into MCP when building sensitive LLM applications.Simon Willison · Simon Willison's Weblog · conf 75%