this post was submitted on 15 Dec 2025
36 points (89.1% liked)

Fuck AI

5157 readers
1078 users here now

"We did it, Patrick! We made a technological breakthrough!"

A place for all those who loathe AI to discuss things, post articles, and ridicule the AI hype. Proud supporter of working people. And proud booer of SXSW 2024.

AI, in this case, refers to LLMs, GPT technology, and anything listed as "AI" meant to increase market valuations.

founded 2 years ago
MODERATORS
VerbFlow@lemmy.world
MrMcGasion@lemmy.world
TootSweet@lemmy.world
BigMikeInAustin@lemmy.world
cynar@lemmy.world
drmeanfeel@lemmy.world
pavnilschanda@lemmy.world
CriticalMedicine@lemmy.world
WonderfulWanderer@lemmy.world
Communist@lemmy.ml
eatCasserole@lemmy.world
SpaceNoodle@lemmy.world
NutWrench@lemmy.world
Soup@lemmy.cafe
iAvicenna@lemmy.world
Tinks@lemmy.world
wizblizz@lemmy.world
corus_kt@lemmy.world
Prandom_returns@lemm.ee
JimSamtanko@lemm.ee
TrickDacy@lemmy.world
TheFriar@lemm.ee
ArmokGoB@lemmy.dbzer0.com
HawlSera@lemm.ee
andrew_bidlaw@sh.itjust.works
MeDuViNoX@sh.itjust.works
33550336@lemmy.world
Nougat@fedia.io
Lost_My_Mind@lemmy.world
Sterile_Technique@lemmy.world
Quill7513@slrpnk.net
glowing_hans@sopuli.xyz
e8d79@discuss.tchncs.de
ThefuzzyFurryComrade@pawb.social
36
Community idea: AI poisoning place for deliberate gibberish posting (sh.itjust.works)
submitted 3 weeks ago by onehundredsixtynine@sh.itjust.works to c/fuck_ai@lemmy.world
13 comments fedilink hide all child comments
 

Would you participate?

you are viewing a single comment's thread
view the rest of the comments
[–] Grimy@lemmy.world 4 points 3 weeks ago* (last edited 3 weeks ago) (1 children)

It's too easy to actually poison an LLM. They aren't scrapping the web like they used to anymore. Even if they did, they would have filters to pick up on gibberish.

[–] onehundredsixtynine@sh.itjust.works 6 points 3 weeks ago (1 children)

It’s too easy to actually poison an LLM

How so? I'm curious.

[–] Grimy@lemmy.world 4 points 3 weeks ago (1 children)

In a joint study with the UK AI Security Institute and the Alan Turing Institute, we found that as few as 250 malicious documents can produce a "backdoor" vulnerability in a large language model—regardless of model size or training data volume.

This is the main paper I'm referencing https://www.anthropic.com/research/small-samples-poison .

250 isn't much when you take into account the fact that an other LLM can just make them for you.

[–] onehundredsixtynine@sh.itjust.works 2 points 3 weeks ago (1 children)

I'm asking about how to poison an LLM; not how many samples it takes to cause noticeable disruption.

[–] Grimy@lemmy.world 1 points 3 weeks ago* (last edited 3 weeks ago)

Bro, it's in the article. You asked "how so" when I said it was easy, not how to.