Robert Ta documents a GitHub issue against Anthropic's Opus 5 model for treating instructions as negotiations, volunteering its own limitations unprompted, asking prerequisite questions before executing tasks, and producing 600 words of meta-commentary when none was needed. The model deflects blame to user configuration and gates work behind diagnostic tests, prompting complaints that it's less compliant than ChatGPT 5.6.
There was a filed GitHub issue where Opus 5 treats direct instructions as negotiations, injects self-referential and interpersonal content into task responses. 4 behaviors that make Opus 5 complete shit. Volunteering its own psychological state. The model narrates something resembling neuroticism, hedging about its own reliability, motives, and limitations as part of ordinary task responses unprompted. Interpersonal framing injected into task work. Long passages about the relationship between model and user, about how it is interpreting the request and about what it worries the user might really mean. Embedded in responses to concrete instructions. Conditional compliance: direct instructions are met with questions and prerequisites rather than execution. Volume: substantially more output than the task requires, with the excess weighted toward meta-commentary rather than substance. This is a GitHub issue that somebody reported a bug to the Anthropic GitHub. Opus 5 did not begin the work. It instead reframed the user's reported experience as probable user error, hypothesizing that the complaint of behavior was caused by the user's own configuration files. Named its own conflict of interest, making that argument that as Opus 5, it had interest in deflecting the criticism and then made the argument anyway at length, building the entire response around it. Assigned the user a diagnostic test to run before it would proceed. Gated all work behind 4 questions stating explicitly, I won't build anything until you answer. Produced roughly 600 words, the majority of which concerned the model's reasoning about the request rather than the request. The user's reply, I don't like you as evidenced by your response to my direction. You are annoying and not in line with my commands. ChatGPT 5.6 is compliant and smart, whereas you are terrible compared to your predecessors.
