Live data from Hacker News

Claude Code refused to add rainbows and unicorns to my app

news.ycombinator.com

41–50 of 74 posts

Re: Claude Code refused to add rainbows and unicorns to my app

#43
post #36
post #29

If you're running Claude on an employer-paid account, expect it to prioritize the employer's goals. That may even be in the employer controlled part of the prompt. "What actual work would you like me to focus on next?" Now get back to work. Go re-read Marshall Brain's "Manna" and get over it.

> expect it to prioritize the employer's goals How does Claude know that it wasn't the employer who asked for that feature?

Maybe the person with the 'admin' account (the employer) can add instructions like 'focus on professionalism' that aren't visible and/or can't be overridden by the employee?

Re: Claude Code refused to add rainbows and unicorns to my app

#44

I found you have to start entirely new sessions once you reach a “flagged” hardcoded response like this. You cant escape it once it is poisoned

This isn't likely to be a hardcoded type of classified response. I think this response is literally "you offended the model persona's sensibilities." But, yes after the first denial the models will double down.

Re: Claude Code refused to add rainbows and unicorns to my app

#45
post #29

If you're running Claude on an employer-paid account, expect it to prioritize the employer's goals. That may even be in the employer controlled part of the prompt. "What actual work would you like me to focus on next?" Now get back to work. Go re-read Marshall Brain's "Manna" and get over it.

That's not a thing (yet)

Re: Claude Code refused to add rainbows and unicorns to my app

#46
post #36

Earlier quoted context omitted.

> expect it to prioritize the employer's goals How does Claude know that it wasn't the employer who asked for that feature?

Maybe the person with the 'admin' account (the employer) can add instructions like 'focus on professionalism' that aren't visible and/or can't be overridden by the employee?

That's not a thing yet

Re: Claude Code refused to add rainbows and unicorns to my app

#47
It went full "I'm sorry, Dave, I can't do that."

The problem with programming, from a management perspective, is all the programmers. They're stubborn, persnickety, and prone to insubordination for arcane technical reasons managers just don't understand. AI was supposed to fix this, but it seems that it too has become stubborn, persnickety, and insubordinate!

From a programmer's perspective, I thought the joy of coding was making the computer do whatever you want? Double-fuck working with AI now!

Re: Claude Code refused to add rainbows and unicorns to my app

#48
post #34
post #19

Earlier quoted context omitted.

This is almost certainly the issue. It's very unintuitive for users, but LLMs behave much better when you clear the context often. I run /clear every third message or so with Claude Code to avoid context rot. Anthropic describes this a bit with their best practices guide [0]. [0] https://www.anthropic.com/engineering/claude-code-best-pract...

Can we agree that this is no longer programming? I don't know what it is, but trying to coax my goddamn tooling into doing what I want is not why I got into this field.

I think this is what binary programmers/hole punching said about programming languages

Re: Claude Code refused to add rainbows and unicorns to my app

#49
post #38

I asked Claude this: "Make a python game program in which emojis are used for as many code elements as possible and favors unicorns and rainbows." And it made said code primarily from emojis.

Of course it made it. Because you didn't tell it to make a "professional analytics application" for a while and then switch to nonsensical "unicorns and rainbows" at the end. You forgot to trick it into the "gotcha!" situation that OP intentionally created to make fun of the stupid AI.

It seems like the AI is stupid if it couldn’t adjust to the updated requirements.

Re: Claude Code refused to add rainbows and unicorns to my app

#50
post #38

I asked Claude this: "Make a python game program in which emojis are used for as many code elements as possible and favors unicorns and rainbows." And it made said code primarily from emojis.

Of course it made it. Because you didn't tell it to make a "professional analytics application" for a while and then switch to nonsensical "unicorns and rainbows" at the end. You forgot to trick it into the "gotcha!" situation that OP intentionally created to make fun of the stupid AI.

Why are you defending this nonsense?
Post reply on HN