You are viewing a single thread.
View all comments View context
14 points

That’s the most straightforward fix. You can’t actually fix the output of an LLM, so you have to run something on the output. You can have it scanned by another AI but that costs money and is also fallible. Regex/delete is the most reliable way to censor.

permalink
report
parent
reply
11 points

Yes, and then the problem is that this doesn’t really scale well. Esp as it is always hard to regexp all the variants correctly without false positives and negatives. Time to regexp html ;).

permalink
report
parent
reply
8 points

Yeah, and you can really see this in image generation. There’s often blocks on using the names of celebrities in the prompts, but if you misspell the names enough it can bypass the censor, and the image generator still understands it.

permalink
report
parent
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

  • 1.5K

    Monthly active users

  • 417

    Posts

  • 11K

    Comments

Community moderators