OpenAI will simply set up a classifier to detect if the client is livenerf, and selectively not nerf those requests.Open models are the endgame.
So make it so all clients pretend to be livenerf at first. Same as the ol' pretending to be Google UA for free articles
I'm not talking about HTTP headers.The classifier is a model; it examines the actual prompt.They already do this for the safety "guardrails".
octoberfranklin · · focus · HN ↗
Open models are the endgame.
paradox460 · · focus · HN ↗
octoberfranklin · · focus · HN ↗
The classifier is a model; it examines the actual prompt.
They already do this for the safety "guardrails".
layla5alive · · focus · HN ↗