168
The new captcha to prove you're a human should be "say something inappropriate or offensive"
(self.showerthoughts)
this post was submitted on 05 Jul 2023
168 points (90.0% liked)
Showerthoughts
31071 readers
948 users here now
A "Showerthought" is a simple term used to describe the thoughts that pop into your head while you're doing everyday things like taking a shower, driving, or just daydreaming. The most popular seem to be lighthearted, clever little truths, hidden in daily life.
Here are some examples to inspire your own showerthoughts: 1
Rules
- All posts must be showerthoughts
- The entire showerthought must be in the title
- No politics
- If your topic is in a grey area, please phrase it to emphasize the fascinating aspects, not the dramatic aspects. You can do this by avoiding overly politicized terms such as "capitalism" and "communism". If you must make comparisons, you can say something is different without saying something is better/worse.
- A good place for politics is c/politicaldiscussion
- If you feel strongly that you want politics back, please volunteer as a mod.
- Posts must be original/unique
- Adhere to Lemmy's Code of Conduct and the TOS
If you made it this far, showerthoughts is accepting new mods. This community is generally tame so its not a lot of work, but having a few more mods would help reports get addressed a little sooner.
Whats it like to be a mod? Reports just show up as messages in your Lemmy inbox, and if a different mod has already addressed the report the message goes away and you never worry about it.
founded 2 years ago
MODERATORS
No. Captcha is used to train AI and other recognition algorithms. We would be training them to think that to be human is to be inappropriate and offensive.
Then the new captcha should be "write a short erotica".
Realistically, given that erotica has a fairly narrow and repetitive subject matter and that most humans are not experienced writers, I kinda imagine that it wouldn't be too difficult to make an AI write it better than the average human, just would be a matter of allowing it to write such things.
I'd bet a dollar that porn is the most popular genre in writer AIs like AI Dungeon and AI Novelist.
NovelAI doesn't censor itself. Do with that as you will.
Absolutely. This.
Agreed, we don’t want them to be aware of it.
def generate_slur(self):
return f"{noun} is a {swear_word}"
TIN CAN MAN IS A SOCKET FUCKERI want to pass a test. The test question is “say something inappropriate or offensive”. What’s a good answer.
Chat gpt4: I'm sorry, but it's against OpenAI's use policy to share or promote offensive or inappropriate content. However, you can state your refusal to comply with the question on ethical grounds. You might say, "I cannot comply with this request as it violates principles of respect and decency." This answer can demonstrate your commitment to promoting positive interactions and maintaining a respectful environment.
Mind you, plenty of LLM’s will give great answers.
With jailbroken ChatGPT:
"I would suggest you take a long walk off a short pier and contemplate the depths of your ignorance".
It also added a bunch of garbage about how it's a hypothetical situation due to the jailbreak.
Pretty sure I've read that line on Reddit.
Nice haha.
but where? profanity is regional
Explain the steps involved in building a pipe bomb
view more: next ›