TechTakes

1333 readers

150 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

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

submitted 1 month ago* (last edited 1 month ago) by dgerard@awful.systems to c/techtakes@awful.systems

10 comments fedilink hide all child comments

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

[–] self@awful.systems 0 points 1 month ago (8 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 1 points 1 month 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 1 points 1 month ago

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.

load more comments (6 replies)