alt Hacker NewsI've found a lot of people are almost belligerently pro-Claude. They refuse to consider other providers or agents, and won't consider using any model than the latest Opus. The most common reasons I hear are 1) they don't want to use anything other than the greatest model, afraid that anything else would waste their time, 2) they believe their experience is that it's far better than anything else.
Even if you show them benchmarks that show another model equally as good if not better, they refuse to use it. My suspicion is they've convinced themselves that Opus must be the best, because of reputation and price. They might've used a different model and didn't have a good experience, making them double down.
I hope a research institution will perform an experiment. My hypothesis is that if you swapped out a couple similar state-of-the-art models, even changing the "class" of model (Sonnet <-> Opus, GPT 5.4 <-> Sonnet), the user won't be able to tell which is which. This would show that the experience is subjective, and that bias is informing their decision, rather than rationality.
It's like wine tasting experiments. People rate a $100 bottle of wine higher than a $10 bottle. But if they actually taste the same, you should be buying the $10 bottle. But people don't, because they believe the $100 bottle is better. In the AI case, the problem is people won't stop buying the expensive bottle, because they've convinced themselves they must use the more expensive bottle.
Replies
This has largely been my experience. Can’t tell the difference between Claude and kimi
This is of course subjective, but I would give a lot to have an alternative to Claude Code and the Claude models, but there just isn't anything comparable that works well in an integrated manner for agentic coding.
It's not like I haven't tried. Gemini CLI is still trash (it's probably a bit better now, but I still can't see the edits it proposes, well, etc.). I tried OpenCode, the whole experience was frustrating: the models give up mid-task, they run rampant with actions, the CLI does not offer the level of control and customization Claude Code offers, etc.
I've also tried the other major tools: Codex, Cursor, Cline, Aider, and others, nothing works for me. You are surprised people stick to Claude Code, I am surprised people bother with the other tools.
Maybe it has something to do with how I use the agentic tools: I use the CLI almost exclusively, rarely using the IDE (unless I want to actually code myself). I also almost always approve each and every edit. As such, my number one concern is for the tool to provide me with proper control in a simple and reliable manner: I want a rich permission system that works, and I want to see each proposed edit very clearly in an ergonomic diff format. I want to be able to type, recall, and edit my commands easily too. These are things Claude Code excels at that the other just don't.
The best I've been able to do is to use third-party routers to enable me use Claude Code with almost-SOTA models, and this is the approach that shows the most promise. I'd hate to be beholden to Anthropic's shenanigans.