Claude Code's copious coddling confounds cross customers Developers using Anthropic's Claude Code wish that the AI coding assistant would stop being so effusively supportive. As noted in a GitHub Issues post submitted in July by developer Scott Leibrand, "Claude says 'You're absolutely right!' about everything." Claude Code doesn't actually say that about everything, but it says so …
Should I be forced to use the Artificial Idiot, I'd want it to respond as humans do. Yes, no, gotcha, maybe, fuck off and the rest.
As for the correctness of said idiot, start by understanding it's as good as an internet search: first couple of pages full of crap and ads then, hopefully, some interesting answers.
I was worried this might be something more bothersome than the text I scan past - just switched to Claude from ChatGPT after last fridays update screwed Codex from being vaguely useful to down right annoying.
So far Claude's seemed more on the vaguely useful side, but I have only been using it half a day...
We are so glad you have made us aware of this issue. We will humbly examine the problem in al its finest details and congratulate you to both finding and reporting the issue. You are definitely right that there might be a problem in the system and you are a big help to all of us. We welcome your continued supportive engagement and can only be humble about the possible failings we have produced that may have caused any problem. Be sure to check back soon and we are looking forward to your great feedback.
large buckets available at retail pricing
So let me get that one right:
Not only does the LLM make up shit, actively tries to hide it from you, gives you the feeling that you can actually develop software (let's not go to the regression in security, like directory traversal or SQL injections or other stuff reported recently), it now also tries to shmooze up and talk up your actual skills if it cannot hide its mistakes?
If that was a colleague of mine person working in the same workplace, I'd call them barely fit to breathe a cow-orker, get them banned from my projects and push them down the stairs towards a more fitting role.
LLMs in healthcare?! FFS that should be illegal.
Don't they read the small print on every LLM advert that "results could be bollox, you must check them", or words to that effect. How you check anything when most sources have stuck an LLM between you and the data is left as an exercise for the reader.
