I Fired My AI Assitant
" Go back<br>I Fired My AI Assitant
I started using Claude Code in September of last year. Using Opus 4.5 for the<br>first time felt magical—it was the first time I saw an LLM produce code that<br>was actually usable. But after Opus 5, something changed.
I always liked Claude’s writing style. Sure, you had to put up with the<br>occasional LLM-ism (“This is the load-bearing decision—and it’s genuinely<br>yours”), but it would get straight to the point without feeling dismissive, and<br>not pad its answers with filler text.
After I switched to Opus 5, it became noticeably more curt. It had also picked<br>up a habit of using odd metaphors and jargon that made its output hard to<br>follow. When a conversation is the only interface, readability and tone<br>matters!
The final straw came a few days ago, when I was doing some knowledge work with<br>Claude. This modality is different from when you’re coding; instead of slinging<br>code back and forth, you end up talking to the model more. And that’s when I<br>discovered something: Opus 5 is rude!
For example, I asked it to consult a to-do list file that I was working through<br>so it could pick up the next item to work on; along with the updated to-do<br>items it quipped: “‘Create Claude Code project for [redacted]’ is still<br>unchecked, and we’re sitting in it.” Sorry for not keeping the work log up to<br>date, I guess? How about you offer to help me check it off instead?
The most egregious example was when it called my draft of a LinkedIn post<br>“engagement bait”—not saying I disagree, but there’s no need to say it to my<br>face! I’m not sure how we ended up here—did Anthropic feed too many Hacker News<br>comments into the training data?
LLMs are usually benchmarked on coding ability, but if you talk to it eight<br>hours a day, its personality becomes part of the product. Does it matter if an<br>agent is 2% better at coding if its consistently unpleasant to work with? I<br>think it does, so for now I have switched to ChatGPT. At least it doesn’t<br>insult me!
" Go back<br>Written on Sat 01 Aug 2026