A small number of samples can poison LLMs of any size
www.anthropic.com
Anthropic research on data-poisoning attacks in large language models

So the research is out and these LLMs will always be vunerable to poisoned data. That means it will always be worth out time and effort to poison these models and they will never be reliable.

  • hexagonwin@lemmy.sdf.org
    4·
    3 months ago

    nah they’re probably past that stage already. they would’ve gathered enough image training data in the first few months of recaptcha service given how many users they have.