Very much smart people (piefedimages.s3.eu-central-003.backblazeb2.com)
 
Post:"this is who you're arguing with online" Picture of a neural network. Reply:"there's too many people with "AI/ML" in their bio asking what this image is"
you are viewing a single comment's thread
view the rest of the comments
[–] 19 points 1 year ago (2 children)

Love this because I completely agree. "We fixed it and it no longer does the bad thing". Uh no, incorrect, unless you literally went through your entire dataset and stripped out every single occurrence of the thing and retrained it, then no there is no way that you 100% "fixed" it

  • source
  • parent
  • hideshow 2 child comments
  • [–] 7 points 1 year ago* (1 child)

    I mean I don't know for sure but I think they often just code program logic in to filter for some requests that they do not want.

    My evidence for that is that I can trigger some "I cannot help you with that" responses by asking completely normal things that just use the wrong word.

  • source
  • parent
  • hideshow 1 child comment
  • It's not 100%, and you're more or less just asking the LLM to behave, and filtering the response through another non-perfect model after that which is trying to decide if it's malicious or not. It's not standard coding in that it's a boolean returned - it's a probability that what the user asked is appropriate according to another model. If the probability is over a threshold then it rejects.

  • source
  • parent