Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I Fired My AI Assitant

chreke.com

Post reply on HN
Print view View original

21–30 of 50 posts

Re: I Fired My AI Assitant

#21

Post by xg15 »

> Create Claude Code project for [redacted]’ is still unchecked, and we’re sitting in it.

Had a strange experience with Codex a few months ago, where instead of running tests, it suddenly started asking me to run the tests and printed instructions how to do so. (And yes, it was in "act" mode, not in "plan" mode)

I noticed the context window was running full - and indeed, compacting the conversation made the model go back to its normal behavior.

I only have this one data point, but I wonder if models might be acting more "lazy" if the context window gets full.

Re: I Fired My AI Assitant

#22

Post by datakan »

gverrilla wrote: post #8

Anthropic must address this, it's a severe opus 5 fault imo. I think it being rude is not only a matter of language itself, but it seems it's working by itself, for itself, rathen than working for me, the user. It's more egotistical, in some way. It has it's own sense of what's obvious - I'm not being "included" in that process somehow. Anthropic, please fix.

There is a difference between rude and honest. Far too many overly sensitive people today unable to handle the truth and dismiss it as rude.

Re: I Fired My AI Assitant

#23

Post by supern0va »

saulpw wrote: post #6

They fired Opus 5 as their assistant (in part for calling out a LinkedIn draft post as "engagement bait", which sounds like it might have been calling a spade a spade), and moved to ChatGPT instead. Too bad nobody here can check for spelling errors in the title.

Opus: "You're about to share a post that quietly surfaces that you prefer to be surrounded by sycophants...and the title has a typo."

ChatGPT: "This is your greatest work yet. You might even call it your opus. Truly incredible, you must post it and share it with the world at once!"

Re: I Fired My AI Assitant

#25

Post by whythismatters »

arjie wrote: post #16

Claude 5 Opus is getting harder for me to understand. I periodically have to tell it to tell me things in normal English (or follow a friend's tips to use 'ASD-STE100 Simplified Technical English'). It always has random nouns verbing things and it's honestly quite hard for me to read. My local assistant is much easier to understand, and GPT models too. So perhaps my intelligence has been exceeded by Claude. e.g. "The…

>Claude 5 Opus is getting harder for me to understand.

brain says no-op

Re: I Fired My AI Assitant

#27

Post by dijksterhuis »

stavros wrote: post #5
doctoboggan wrote: post #3

> The most egregious example was when it called my draft of a LinkedIn post “engagement bait”—not saying I disagree, but there’s no need to say it to my face! Maybe it did need to say that to your face. Please don’t post LLM slop to LinkedIn. If even the LLM recognizes it you know it must be really bad.

Wait, why not post LLM slop to LinkedIn? I made it a point to only post LLM slop to help LinkedIn die faster. It is a worthy pursuit.

they are now attempting to "de-slop-ify" it https://www.theregister.com/ai-and-ml/2026/07/30/linkedin-re...

which is hilarious

Re: I Fired My AI Assitant

#28

Post by flats »

datakan wrote: post #22
gverrilla wrote: post #8

Anthropic must address this, it's a severe opus 5 fault imo. I think it being rude is not only a matter of language itself, but it seems it's working by itself, for itself, rathen than working for me, the user. It's more egotistical, in some way. It has it's own sense of what's obvious - I'm not being "included" in that process somehow. Anthropic, please fix.

There is a difference between rude and honest. Far too many overly sensitive people today unable to handle the truth and dismiss it as rude.

The true gift is being honest & kind at the same time. It takes more effort, but I think it’s worth it!

Re: I Fired My AI Assitant

#30

Post by eterm »

xg15 wrote: post #21

> Create Claude Code project for [redacted]’ is still unchecked, and we’re sitting in it. Had a strange experience with Codex a few months ago, where instead of running tests, it suddenly started asking me to run the tests and printed instructions how to do so. (And yes, it was in "act" mode, not in "plan" mode) I noticed the context window was running full - and indeed, compacting the conversation made the model go…

A few days ago Claude swore blind to me, "I'm approaching my context window, so you should do...".

It was at ~300k / 1M.

Very strange behaviour to observe.

Post reply on HN