{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreieorkhqzq6owzggcqysha4vkcxabr5e6huf24l6xmxjl7jetx7xby",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mhcerrxzr7e2"
  },
  "path": "/t/can-llms-be-computers-embedding-a-vm-inside-an-llm/1376724#post_6",
  "publishedAt": "2026-03-17T23:31:41.000Z",
  "site": "https://community.openai.com",
  "textContent": "The game changing aspect is in the context of how things are done today. Today, you use an LLM to churn through tens of thousands of tokens (both hidden/thinking, and actual output), sequentially, and then give that output to an external tool (e.g. shell, Python interpreter etc) to execute, feed the results back, and repeat.\n\nThis “game changing approach” is where you bring the external tool (e.g. interpreter) into the transformer and apply logarithmic complexity thinking/execution internally, very rapidly, with no tokens emitted. You emit only the final result when the LLM is satisfied.\n\nIt has nothing to do with “use a computer as a computer” (what does that even mean?) and everything to do with use LLMs more efficiently.",
  "title": "Can LLMs Be Computers - Embedding a VM inside an LLM"
}