←back to thread

The Monster Inside ChatGPT

(www.wsj.com)
46 points petethomas | 1 comments | 27 Jun 25 14:16 UTC | HN request time: 0.205s | source
Show context
gchamonlive ◴[27 Jun 25 15:04 UTC] No.44397333[source]▶
If you put lemons in a blender and add water it'll produce lemon juice. If you put your hand in a blender however, you'll get a mangled hand. Is this exposing dark tendencies of mangling bodies hidden deep down blenders all across the globe? Or is it just doing what's supposed to be doing?

My point is, we can add all sorts of security measures but at the end of the day nothing is a replacement for user education and intention.

replies(4): >>44397460 #>>44397741 #>>44397742 #>>44397831 #
dghlsakjg ◴[27 Jun 25 15:48 UTC] No.44397741[source]▶
The scary part is that no one put their hand in the blender. They put a rotten fruit in and got mangled hand bits out.

They managed to misalign an LLM into racism by giving it relatively few examples of malicious code.

replies(2): >>44397828 #>>44403664 #
1. bilbo0s ◴[27 Jun 25 16:00 UTC] No.44397828[source]▶
I believe the point HN User gchamonlive is making is that the mangled hands were already in the blender.

The base model was trained, in part, on mangled hands. Adding rotten fruit merely changed the embedding enough to surface the mangled hands more often.

(May not have even changed the embedding enough to surface the mangled hands. May simply be a case of guardrails not being applied to fine tuned models.)