Why Nostr? What is Njump?
2024-02-24 23:31:32
in reply to

Dana Fried on Nostr: npub1q9ma5…lzgdu it's interesting because LLMs self-poison if they ingest too much ...

it's interesting because LLMs self-poison if they ingest too much of their output; also more people are using image poisoning tools.

So, there may come a point where we can no longer safely train models on new data.
Author Public Key
npub1syuuldp8kpkhpy3ugeatr66u2teht3ynl8h6ynvdv0z7ywmy7c5qctel2e