{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreics6ih2ovqvxyd2zmgeevwbhez2oi34gucvmtx3x65br6wmwnabvi",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mgzy2jci3a22"
  },
  "path": "/t/can-llms-be-computers-embedding-a-vm-inside-an-llm/1376724#post_1",
  "publishedAt": "2026-03-14T16:05:33.000Z",
  "site": "https://community.openai.com",
  "tags": [
    "Can LLMs Be Computers? | Percepta"
  ],
  "textContent": "This paper blew me away: Can LLMs Be Computers? | Percepta\n\nThe entire agentic ecosystem today, from Claude Code to Codex to OpenClaw, is based on the principle of surrounding LLMs - which are simply token distribution generators - with external tools (Python, git, curl, APIs, MCPs), and a state machine. An LLM cannot reliably “execute” a mathematical expression - it can talk/reason about it; it can (if seen in the training data) “guess” the result; it can produce Python code to run (externally) in a Python sandbox, and use the result in its answer.\n\nWhat the folks in this paper did, was turn the LLM into a virtual machine (VM), and effectively use the transformer weights as a fast WebAssembly interpreter. The result: you give an LLM a program, it ACTUALLY executes the program by emitting a stack trace (internally), and it outputs the result!\n\nThey took a vanilla PyTorch Transformer architecture (couple of dozen lines of code), and embedded WebAssembly in model weights by training the transformer to predict state transitions of a WASM virtual machine, so the attention and MLP layers collectively implement the interpreter’s logic. Programs are fed as tokens, and the network simulates execution step-by-step.\n\nIf it holds true, this could be an absolute game changer. Imagine you somehow integrate this into a GPT model, i.e. you effectively embed a code interpreter “inside” the LLM weights. Then instead of using costly/inefficient thinking/reasoning tokens, you are instead using an internal logarithmic-complexity state emission to literally compute or “run” something, before finally emitting tokens.\n\nAnyway, it got me very excited, and I’m wondering if OpenAI peeps are looking into this?\n\n\n",
  "title": "Can LLMs Be Computers - Embedding a VM inside an LLM"
}