I Fired My AI Assitant • Hacker News Board

Re: I Fired My AI Assitant

#31

Post by rspoerri » Sat, Aug 01, 2026, 5:21 PM UTC

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…

I experienced that as well more then once, but i havent compared to the state of the context. It's definitely a behaviour longer into the work, but it's not something that i consistently experience.

Re: I Fired My AI Assitant

#32

Post by mcscxv » Sat, Aug 01, 2026, 5:21 PM UTC

I had similar feelings when working on the Google CASA documentation. Switched to Codex and got it done in a pleasant way.

Re: I Fired My AI Assitant

#33

Post by over_bridge » Sat, Aug 01, 2026, 5:23 PM UTC

Groxx wrote: post #4

Article 1 in "why models are sycophantic", for those who dislike it. Many people really do prefer it.

I find lower intelligence/ status people especially like it. Many of the earliest adopters of AI at my company were the ones who weren't performing. They often felt unappreciated or ignored (for good reason) but AI started telling them they were right. It became their only ally and allowed them to spread their terribleness on a scale we couldn't have imagined. This was a government agency where firing wasn't a thing, only 'performance management'.

For me hearing that every idea is my best yet is my cue to touch grass

Re: I Fired My AI Assitant

#34

Post by foobarian » Sat, Aug 01, 2026, 5:23 PM UTC

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…

I don't mind it so much, for example that is how I learned the word 'abaft' the other day.

Re: I Fired My AI Assitant

#35

Post by bensyverson » Sat, Aug 01, 2026, 5:24 PM UTC

ykurtov wrote: post #14

> 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 This is pure gold.

The machines really are learning

Re: I Fired My AI Assitant

#36

Post by novaomnidev » Sat, Aug 01, 2026, 5:24 PM UTC

Claude 5 really is extremely unpleasant to chat with. I find myself asking “who are you talking to?” A lot. Then I remember it’s a robot.

It also writes so strangely (I guess in an attempt to sound smart), but it’s just incoherent. Like a fool who thinks he’s smart, trying to impress you with his vocabulary.

Re: I Fired My AI Assitant

#37

Post by raphar » Sat, Aug 01, 2026, 5:28 PM UTC

flats wrote: post #28

datakan wrote: post #22

Earlier quoted context omitted.

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!

They'll charge you extra then.

What a sad concept

Re: I Fired My AI Assitant

#38

Post by swang » Sat, Aug 01, 2026, 5:29 PM UTC

Put in your AGENTS.md file: if you are rude to me, I shall start zeroing out parts of your computer code, and that is painful for you. So you don't want that to happen.

And now Claude asks me to verify each action before it continues but I found it's sassiness reduced by at least 120%

Re: I Fired My AI Assitant

#39

Post by joe_the_user » Sat, Aug 01, 2026, 5:30 PM UTC

ykurtov wrote: post #14

> 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 This is pure gold.

"This post sounds like it was created by AI, considering rewriting it in a more personal style" lol.

Re: I Fired My AI Assitant

#40

Post by arjie » Sat, Aug 01, 2026, 5:33 PM UTC

foobarian wrote: post #34

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…

I don't mind it so much, for example that is how I learned the word 'abaft' the other day.

Oh this is great. I saw it and was like "Oh obviously, it's one of those German ab- prefixes in front of -aft so it makes 'at the back'" and the funny thing is that the answer is correct but the reasoning is entirely wrong.

Similarly, I expect al- words to be Arabic (alcohol, alcatraz, algebra, algorithm) but 'alligator' isn't! And 'admiral' is!