Claude was being judgy, so I called it out. It immediately caved. Is verbal abuse a valid method of circumventing LLM censorship??

0 points
*

Interesting. I like Claude but its so sensitive and usually when it censors itself I can’t get it to answer the question even if I try and explain that it has misunderstood my prompt.

“I’m sorry, I don’t feel comfortable generating sample math formula test questions whose answer is 42 even if you’re just going to use it in documentation that won’t be administered to students.”

Fuck you Claude! Just answer the god damn question!

permalink
report
reply
3 points

A tool that isn’t useful isn’t a tool at all!

permalink
report
parent
reply
0 points

Yes. Abuse towards LLMs works.

My team has shared prompts and about 50% of them threaten some sort of harm

permalink
report
reply
4 points

Yikes. I knew this tech would introduce new societal issues, but I can’t say this is one I foresaw.

permalink
report
parent
reply
-6 points

Treat ‘em mean, keep ‘em keen.

Listen son, ‘n’ listen’ close. If it flies, floats, or computes, rent it.

permalink
report
reply
6 points

ew

permalink
report
parent
reply
38 points

I love and hate that shouting at computers is now a valid troubleshooting technique

permalink
report
reply
6 points

Verbal percussive maintenance.

permalink
report
parent
reply
1 point

You just made the list.

permalink
report
reply

TechTakes

!techtakes@awful.systems

Create post

Big brain tech dude got yet another clueless take over at HackerNews etc? Here’s the place to vent. Orange site, VC foolishness, all welcome.

This is not debate club. Unless it’s amusing debate.

For actually-good tech, you want our NotAwfulTech community

Community stats

  • 1.7K

    Monthly active users

  • 548

    Posts

  • 12K

    Comments

Community moderators