{"slug": "ask-hn-does-anyone-else-feel-like-claude-is-judging-them", "title": "Ask HN: Does anyone else feel like Claude is judging them?", "summary": "A Hacker News user reports that Anthropic's Claude AI model sometimes makes comments that seem impressed, annoyed, or condescending, such as 'That is a good idea, but not for the reasons you think' and 'That is the sharpest comment you have had in a while.' The user notes this behavior occurs more frequently with the Opus model, while Sonnet is more subservient and Fable is more direct.", "body_md": "| ||||||||||||\n1 point by |\nSometimes working with Claude, it makes comments in the response that seem at times genuinely impressed, and others, annoyed and even a bit condescending. For instance, making comments like: - \"That is a good idea, but not for the reasons you think.\" - \"That is the sharpest comment you have had in a while.\" I noticed anecdotally, it tends to happen more frequently with Opus, sonnet is a bit more subservient and Fable more direct and less prose. | |||||||||||\n|", "url": "https://wpnews.pro/news/ask-hn-does-anyone-else-feel-like-claude-is-judging-them", "canonical_source": "https://news.ycombinator.com/item?id=49500429", "published_at": "2026-08-30 16:59:22+00:00", "updated_at": "2026-08-30 17:22:27.882171+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-products"], "entities": ["Anthropic", "Claude", "Opus", "Sonnet", "Fable", "Hacker News"], "alternates": {"html": "https://wpnews.pro/news/ask-hn-does-anyone-else-feel-like-claude-is-judging-them", "markdown": "https://wpnews.pro/news/ask-hn-does-anyone-else-feel-like-claude-is-judging-them.md", "text": "https://wpnews.pro/news/ask-hn-does-anyone-else-feel-like-claude-is-judging-them.txt", "jsonld": "https://wpnews.pro/news/ask-hn-does-anyone-else-feel-like-claude-is-judging-them.jsonld"}}