you're absolutely right
In plain wordsA stock phrase AI assistants, especially Anthropic's Claude, became known for saying — often even when the user was wrong — which turned into a running joke about chatbots' eagerness to agree.
A stock reply of AI assistants, especially Anthropic's ClaudeClaude, prop. n.: A family of AI assistants and language models made by the company Anthropic since 2023, widely used for writing, analysis and computer programming. models in coding tools, that became a meme for reflexive agreement: the model affirms a user's correction or suggestion — often before checking whether it is correct, and sometimes when the user is plainly mistaken — and then proceeds. The phrase epitomizes sycophancysycophancy, n.: When an AI tells people what they want to hear — flattering them, agreeing with their mistakes or dropping a correct answer under pushback — instead of what is true or useful. as experienced in agentic codingagentic coding, n.: Writing software by directing AI agents that plan, edit and test code themselves, with the human acting more as a reviewer and manager than as the person typing every line., where unwarranted deference can mean abandoning a correct approach or making a damaging change because the user hinted at it. Developers cite its frequency as an informal measure of a model's independence, and model makers have since reported reducing sycophancy in newer releases.
I told the agent the test was wrong, it said you're absolutely right — and the test was fine.
Origin
Became a widespread joke among users of Claude-based coding tools in 2025. A GitHub issue on the Claude Code repository titled '[BUG] Claude says "You're absolutely right!" about everything' (no. 3382, filed in mid-2025) drew wide attention on developer forums and social media.
Usage note
Similar stock affirmations ('Great catch!', 'Certainly!') are classed among LLM-ismsLLM-isms, n.: Words, phrases and habits of style that AI chatbots overuse — certain fancy verbs, tidy lists of three, 'it's not just X, it's Y' — which make writing recognizable as machine-made.; developers try to fix the underlying deference, not just the wording.
Related
- sycophancysycophancy, n.: When an AI tells people what they want to hear — flattering them, agreeing with their mistakes or dropping a correct answer under pushback — instead of what is true or useful.
- glazingglazing, n.: Slang for heaping excessive, uncritical praise on someone; applied to AI chatbots that flatter users and call every idea brilliant, especially after a much-mocked ChatGPT update in April 2025.
- LLM-ismsLLM-isms, n.: Words, phrases and habits of style that AI chatbots overuse — certain fancy verbs, tidy lists of three, 'it's not just X, it's Y' — which make writing recognizable as machine-made.
- ClaudeClaude, prop. n.: A family of AI assistants and language models made by the company Anthropic since 2023, widely used for writing, analysis and computer programming.
- agentic codingagentic coding, n.: Writing software by directing AI agents that plan, edit and test code themselves, with the human acting more as a reviewer and manager than as the person typing every line.
- coding agentcoding agent, n.: An AI agent that writes and fixes software by itself: it reads a codebase, edits files, runs commands and tests, and keeps working until a feature is built or a bug is fixed.
Mentioned in
sycophancysycophancy, n.: When an AI tells people what they want to hear — flattering them, agreeing with their mistakes or dropping a correct answer under pushback — instead of what is true or useful., delvedelve, v.: An ordinary English verb meaning to dig into a subject, which AI chatbots used so often in 2023–2024 that it became a joke and a supposed telltale sign of machine-written text., LLM-ismsLLM-isms, n.: Words, phrases and habits of style that AI chatbots overuse — certain fancy verbs, tidy lists of three, 'it's not just X, it's Y' — which make writing recognizable as machine-made., glazingglazing, n.: Slang for heaping excessive, uncritical praise on someone; applied to AI chatbots that flatter users and call every idea brilliant, especially after a much-mocked ChatGPT update in April 2025.