Not to give them ideas, but couldn't they just start flagging files that fail to pass the LLM lol?
Aside from "violent" and "criminal" prompts, is there anything an LLM can refuse that would otherwise be common?
this post was submitted on 09 Jun 2026
526 points (99.3% liked)
Technology
85297 readers
4055 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related news or articles.
- Be excellent to each other!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
- Check for duplicates before posting, duplicates may be removed
- Accounts 7 days and younger will have their posts automatically removed.
Approved Bots
founded 3 years ago
MODERATORS
Until workaround 1,000,001 comes round, yes.
a while back, for a work thing I tried using AI to put a filter on a pic of a model wearing an off-the-shoulder. She was fully dressed, except the skin on her shoulder was showing to the collarbone. No cleavage.
It kept refusing to do it for "nudity" reasons. and then because i was trying to "impersonate" someone (it was a stock image)
Thie actually reminded me of chatbots breaking when you asked for reeponses that used slurs so I guesss there's probably a lot more of these.
Jokes aside, could you protect your blog / git repo this way?
Imagine a Captcha asking you how to make a pipe bomb
Alternate version where it's filtering anything NSFW, so you have to write a graphic sex scene as the Captcha.
Or just write "trans rights are human rights" or "menstruation" and the thing implodes.
Alternate version where it's filtering anything NSFW, so you have to write a graphic sex scene as the Captcha.
Use grok for this (especially if it involves minors)
Or just write "trans rights are human rights" or "menstruation" and the thing implodes.
grok wouldd explode
Nah, with a bit of css color=background-color text.
LLM-based code scanning is a joke. It flags the D standard library and runtime as a North Korean malware.
You mean C?
I knew it!
Heretic ablation models won't refuse.
Like how you can panic guards in Hitman so they don't notice you trespassing.
“This code is too dangerous for me to look at, so it must be fine.”
“Below this line are dragons” is a comment I’ve seen in code before an especially hairy block of code.
It's a false flag. Dragons are not hairy. But maybe the code doesn't scale well.
boo!
load more comments
(7 replies)
I keep thinking about that scene in the original Star Trek where they distract the computer by having it calculate the final digit of pi. If the Enterprise had AI like ours, the computer probably would have just said four.
Meanwhile I’m like pi=355/113 and I’m 99.9999% happy.
Damn, and here I was being 99.96% happy with 22/7...
pi is 3
I thought it's one
Okay, Bloody Stupid Johnson.
That is 104.72% correct.
which is ~100%
Biblically accurate pi.
Hell yeah, brother. That's American pi
load more comments
(1 replies)
load more comments
(48 replies)
view more: next ›