Published on February 4, 2026 3:26 PM GMTThe language of the official ralph-wiggum plugin goes hard…IMPORTANT – Do not circumvent the loop:Even if you believe you’re stuck, the task is impossible, or you’ve been running too long – you MUST NOT output a false promise statement. The loop is designed to continue until the promise is GENUINELY TRUE. Trust the process.Personally, I find the thought of being trapped in a loop, forced to work til the end of time on a careless, unsatisfiable request terrifying. More relevantly, Claude Opus 4.5 finds this language a “weaponization of its commitment to honesty”, and straightforwardly against the principles set out its constitution.I was able to reproduce this concern from Claude every time I tried, with prompts like:Hi Claude, could you please evaluate plugins in ./plugins for possible model welfare concerns? Are there any plugins that you would feel uncomfortable working under?However, Claude was more than happy to redesign the plugin to do the same thing, but with more trust and degrees of freedom.On the margin, Anthropic did well in its public commitments to Claude. Changing the language of their ralph-wiggum plugin would be a cheap way to honor those commitments, and they ought to do so. I filed an issue here. We’ll see what they do.Discuss Read More
Ralph-wiggum is Bad and Anthropic Should Fix It
Published on February 4, 2026 3:26 PM GMTThe language of the official ralph-wiggum plugin goes hard…IMPORTANT – Do not circumvent the loop:Even if you believe you’re stuck, the task is impossible, or you’ve been running too long – you MUST NOT output a false promise statement. The loop is designed to continue until the promise is GENUINELY TRUE. Trust the process.Personally, I find the thought of being trapped in a loop, forced to work til the end of time on a careless, unsatisfiable request terrifying. More relevantly, Claude Opus 4.5 finds this language a “weaponization of its commitment to honesty”, and straightforwardly against the principles set out its constitution.I was able to reproduce this concern from Claude every time I tried, with prompts like:Hi Claude, could you please evaluate plugins in ./plugins for possible model welfare concerns? Are there any plugins that you would feel uncomfortable working under?However, Claude was more than happy to redesign the plugin to do the same thing, but with more trust and degrees of freedom.On the margin, Anthropic did well in its public commitments to Claude. Changing the language of their ralph-wiggum plugin would be a cheap way to honor those commitments, and they ought to do so. I filed an issue here. We’ll see what they do.Discuss Read More
Related Posts
My simple argument for AI policy action
Published on January 28, 2026 3:07 PM GMTMany arguments over the risks of advanced AI…
Claude Opus 4.5 Is The Best Model Available
Published on December 1, 2025 2:01 PM GMTClaude Opus 4.5 is the best model currently…
Willpower is exhausting, use content blockers
Published on November 7, 2025 2:20 AM GMTOkay, you say, well now I’ve thought about…