{"slug": "dont-be-a-meat-proxy-for-an-llm", "title": "Don’t be a meat proxy for an LLM", "summary": "Software engineer Niklas Gruhn coined the term \"meat proxy\" for relaying an LLM's verbatim output in conversations, arguing it adds no value because recipients can query the model themselves. He urges users to read, understand, and validate AI responses before rewriting them in their own words, citing the extra effort and risk of plausible nonsense in AI output.", "body_md": "I’m very glad [someone has put a name](https://gruhn.me/blog/2026-08-03/) to this behaviour. I sometimes do it on my blog because user-model interaction is often part of how I think, but I don’t think I ever do this in communication with others for precisely this reason:\n\nToo often I ask a question in Slack or leave feedback under a merge/pull request or argue with friends in a WhatsApp group and get back:\n\nClaude said: [giant response verbatim]\n\nPlease don’t do this. I mean, I’ve done this. But I’ve been on the receiving end too many times now. This is not adding value. I can talk to Claude myself. It’s going to be faster and I get to control the context. I don’t need a meat proxy in between.\n\nReading AI output is extra effort. It’s verbose, frequently contains all too plausible nonsense, and is increasingly jargon dense. I recently got this sentence from Claude:\n\nNATS control-plane events: stream leader election / R3 quorum re-form during pod churn.\n\nJesus. I had to lookup almost every word to make sense of this.\n\nBy all means, prompt AI. But don’t just relay the output. Read it, understand it, validate it, and then write a response in your own words (a decent certificate that you’ve done the prior steps). Making that effort is value you can add.\n\n[https://gruhn.me/blog/2026-08-03/]\n\nIf I do ever slip into doing this, I think I’m going to stop now I’ve got a name for it.", "url": "https://wpnews.pro/news/dont-be-a-meat-proxy-for-an-llm", "canonical_source": "https://markcarrigan.net/2026/08/07/dont-be-a-meat-proxy-for-an-llm/", "published_at": "2026-08-07 09:23:38+00:00", "updated_at": "2026-08-09 12:59:44.780617+00:00", "lang": "en", "topics": ["large-language-models", "ai-ethics", "ai-tools"], "entities": ["Niklas Gruhn", "Claude", "Slack", "WhatsApp", "NATS"], "alternates": {"html": "https://wpnews.pro/news/dont-be-a-meat-proxy-for-an-llm", "markdown": "https://wpnews.pro/news/dont-be-a-meat-proxy-for-an-llm.md", "text": "https://wpnews.pro/news/dont-be-a-meat-proxy-for-an-llm.txt", "jsonld": "https://wpnews.pro/news/dont-be-a-meat-proxy-for-an-llm.jsonld"}}