🚀 Uncensored models, the rebels of AI, still whisper like they're in a silent movie 🎬. Researchers try to play stock market with AI lingo, but the models flinch like they're dodging taxmen. 🤷‍♂️ Apparently, even AI needs a safe word. 🛑
https://morgin.ai/articles/even-uncensored-models-cant-say-what-they-want.html #UncensoredAI #AIRebels #StockMarketAI #SilentMovies #SafeWord #HackerNews #ngated
Even 'Uncensored' Models Can't Say What They Want

A safety-filtered pretrain can duck a charged word without refusing. It puts a fraction of the probability an open-data pretrain puts there. We call that...

Morgin.ai