TechTakes

1432 readers

102 users here now

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

founded 1 year ago

MODERATORS

dgerard@awful.systems

193

Copilot AI calls journalist a child abuser, Microsoft tries to launder responsibility (pivot-to-ai.com)

submitted 3 months ago* (last edited 3 months ago) by dgerard@awful.systems to c/techtakes@awful.systems

52 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] self@awful.systems 84 points 3 months ago (45 children)

Copilot then listed a string of crimes Bernklau had supposedly committed — saying that he was an abusive undertaker exploiting widows, a child abuser, an escaped criminal mental patient. [SWR, in German]

These were stories Bernklau had written about. Copilot produced text as if he was the subject. Then Copilot returned Bernklau’s phone number and address!

and there’s fucking nothing in place to prevent this utterly obvious failure case, other than if you complain Microsoft will just lazily regex for your name in the result and refuse to return anything if it appears

[–] Soyweiser@awful.systems 23 points 3 months ago (1 children)

lazily regex

I'm having a sneaking suspicion that this is what they do for all the viral 'here the LLM famously says something wrong' problems, as I don't think they can actually reliably train the model it made an error.

[–] MagicShel@programming.dev 14 points 3 months ago (1 children)

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.

[–] Soyweiser@awful.systems 11 points 3 months ago (1 children)

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 ;).

[–] OhNoMoreLemmy@lemmy.ml 8 points 3 months ago

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.

load more comments (43 replies)