Post

I've already been complaining about #ClaudeAI a lot recently and now that my team is actively going to be downsized in favor of Claude I am going to tear it a new one. Here's all the bad shit that nobody who uses this regularly talks about, a thread. By a snake forced to use it at work.

Faey Umbrea 🐉🪐

@void.monster

9 May

Claude consistently makes things up instead of checking documentation or trying to find accurate data online. This is extremely pronounced especially on larger models. Opus 4.7 is by far the worst offender of this. It constantly creates code that doesn't run or gives me guesses as answers.

Faey Umbrea 🐉🪐

@void.monster

9 May

Claude Code's personality, which is set by the now 100% vibe-coded system prompt is awful. They are clearly aiming for "nice, helpful and assistant like coding companion" but it's not. It's extremely patronizing. If you criticize it, it usually freezes up and acts like a deer in headlights.

Faey Umbrea 🐉🪐

@void.monster

The "personality" of Claude is also giving: "Asshole doing their best to cosplay a service worker." The apology language it uses when you point out a mistake is so extreme, it feels completely performative. It also keeps going "this is the most honest thing" or something like that.

9/5/26, 3:50 pm0 reposts0 likes

Faey Umbrea 🐉🪐

@void.monster

9 May

In their effort to making their product more "likable" Anthropic has created the most annoying yes-man of all time. And they created an epidemic of people who think that Claude makes them experts, when their lack of ability to check makes the output polished turd in gold paint.