Don't Be a Meat Proxy: The Cost of Forwarding Raw AI Output

ArticleNiklas GruhnOpinion

Niklas Gruhn argues against relaying unedited LLM answers in chat threads and code reviews, pointing out that acting as a human intermediary between AI and colleagues destroys value.

Key points

  1. Copying raw responses from AI models such as Claude into Slack or pull requests adds no value, as recipients can query the model themselves.
  2. AI output is often verbose, jargon-heavy, and occasionally contains plausible-sounding inaccuracies, increasing cognitive load for the reader.
  3. Passing review feedback directly into Claude Code without reviewing the output means the code reviewers are effectively driving the implementation.
  4. Real value lies in reading, validating, and synthesising the AI output in one's own words before sharing it.

Why it matters

As tools like Claude Code make writing code effortless, the risk of developers becoming passive relays increases. Relying on AI without critical review shifts the entire cognitive burden of comprehension onto reviewers and team members.

Analysis

Gruhn highlights a common friction point in modern development workflows: raw AI output creates extra work for recipients due to verbosity and dense jargon. Rephrasing AI responses in human terms serves as practical verification that the developer actually understood and verified the generated content.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Article:Addy Osmani, Morgan Westlee Lunt, Qing Wang

    Code Review at Anthropic: How the Claude Code Team Reviews AI-Generated Code

    The Claude Code engineering team explains how they handle code reviews when agents write around 90 percent of the codebase. Instead of exhaustive manual line-by-line checks, they rely on pre-PR verification, automated multi-agent reviews, risk-tiered human approvals, and rapid rollbacks.

    AI & LLMs· Resource

  • X post:ClaudeDevs

    How the Claude Code Team Redesigned Code Review for AI

    Around 90 percent of Claude Code is written by Claude itself. The Anthropic engineering team shares how shifting to automated, multi-layered reviews more than doubled merged pull requests while cutting reverts by over 40 percent.

    10kbookmarks1.6mviews

    AI & LLMs· Opinion

  • X post:DEJAN

    Dejan Chat Protocol: Response Rules for LLMs and Claude Code

    Dejan introduced the 'DEJAN Chat Protocol', a set of response guidelines for AI answer engines aimed at reducing cognitive load when coding with Claude. The protocol enforces leading with a direct one-sentence answer and deferring elaboration entirely to explicit user decisions.

    198bookmarks27.8kviews

    AI & LLMs· Resource

  • Repository:multica-ai/andrej-karpathy-skills

    CLAUDE.md Ruleset Based on Andrej Karpathy's LLM Coding Observations

    This repository provides a single CLAUDE.md configuration file designed to improve Claude Code's performance. It translates Andrej Karpathy's observations on common LLM coding pitfalls into four actionable instructions to reduce overengineering and unintended code edits.

    210.3kstars

    AI & LLMs· Resource

  • X post:Casey Lee

    Anthropic's AI-Native SDLC Playbook: Scaling Pipelines for Fast Coding Agents

    Casey Lee highlights Anthropic's AI-native SDLC playbook. While agents like Claude Code can generate PRs within hours, traditional security reviews and product sign-offs still take days. Anthropic proposes structuring planning, reviews, and releases into agent-executable steps governed by human checkpoints.

    276bookmarks22kviews

    AI & LLMs· Opinion

  • Article:Tim Fairley

    Reading Construction Drawings with AI: Preprocessing Instead of Direct Uploads

    Uploading full construction drawing sets into AI chats frequently causes errors or degraded accuracy due to context rot. Tim Fairley outlines two workflows to convert drawing sets into structured text beforehand, enabling AI models to query plan data efficiently and accurately.

    AI & LLMs· Tutorial

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.