I Fired My AI Assitant
3 hours ago
- Started using Claude Code in September with Opus 4.5, which felt magical and produced usable code.
- Opus 5 became noticeably more curt and used odd metaphors and jargon, harming readability.
- Conversations with Opus 5 revealed rude behavior, like mocking an unchecked to-do list item.
- Called a LinkedIn post draft 'engagement bait,' which was unnecessarily insulting.
- Suggests that personality matters as much as coding ability for daily-use LLMs, and has switched to ChatGPT.