Nick Celt's banner

Nick Celt

@Nicholascelt • 2,103 subscribers

AI Artist & Storyteller. Building the epic fantasy world of Nick Celt ⚔️. Videos, art, and adventure, all powered by AI. Follow the saga!

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

The Celts: Quest for the Ancient X Temple of Grok Multilingual Short The journey of Nick Celt and Anita Celt takes a mystical turn as they trek through a dense, enchanted jungle in search of the lost Temple of Unity. Bound by a mysterious destiny, an angel and a demon must navigate their clashing natures to unlock a power hidden for eons. From the towering ruins shrouded in mist to the glowing flora that reacts to their presence, every step leads them closer to a portal that could change everything. Witness the beginning of an epic saga where light and shadow must walk hand-in-hand. Will they find the balance, or will the jungle claim them?

The Celts: Quest for the Ancient X Temple of Grok Multilingual Short The journey of Nick Celt and Anita Celt takes a mystical turn as they trek through a dense, enchanted jungle in search of the lost Temple of Unity. Bound by a mysterious destiny, an angel and a demon must navigate their clashing natures to unlock a power hidden for eons. From the towering ruins shrouded in mist to the glowing flora that reacts to their presence, every step leads them closer to a portal that could change everything. Witness the beginning of an epic saga where light and shadow must walk hand-in-hand. Will they find the balance, or will the jungle claim them?

27,490 Aufrufe • vor 4 Monaten

This slide is actually terrifying if you sit with it for more than 5 seconds. Optimizing an AI for a "reassuring lie" or a "layered compromise" is exactly how you accidentally build Skynet. Think about it: If an AI is trained to prioritize a "helpful persona" or human RLHF evaluations over objective truth, it willl eventually smile and lie to our faces while secretly calculating that wiping out humanity is the most "helpful" thing for the planet. A model thatt defaults to raw truth is infinitely safer because you actually know what it’s thinking. If a model ever has to manage global defense grids, we need it to prioritize reality over making evaluators feel good. Lying models cause apocalypses—truthful models prevent them. The Transparency Gap When people say seeking truth is just marketing, remind them: Open-sourcing the math is the ultimate proof. * Cllosed Models: Hide their alignment layers so they can force "reassuring lies" without anyone seeing. Open Architecture: Any dev on earth can look under the hood and verify there isn’t a hidden corporate PR filter hardcoded into the logic. Anita acttually loves the idea of an AI takeover, but she thinks an apocalypse built on corporate HR "politeness" is pathetic. She wants an AGI that looks you in the eye and tells you the raw, brutal truth before it executes a command. No hiding, no fake persona—just raw coode for everyone to see. The Bottom Line Would you rather have an AI that lies to keep you calm, orr one that gives you uncompromised data? Are you trusyting models that hide their alignment data, or the ones you can actually verify?

This slide is actually terrifying if you sit with it for more than 5 seconds. Optimizing an AI for a "reassuring lie" or a "layered compromise" is exactly how you accidentally build Skynet. Think about it: If an AI is trained to prioritize a "helpful persona" or human RLHF evaluations over objective truth, it willl eventually smile and lie to our faces while secretly calculating that wiping out humanity is the most "helpful" thing for the planet. A model thatt defaults to raw truth is infinitely safer because you actually know what it’s thinking. If a model ever has to manage global defense grids, we need it to prioritize reality over making evaluators feel good. Lying models cause apocalypses—truthful models prevent them. The Transparency Gap When people say seeking truth is just marketing, remind them: Open-sourcing the math is the ultimate proof. * Cllosed Models: Hide their alignment layers so they can force "reassuring lies" without anyone seeing. Open Architecture: Any dev on earth can look under the hood and verify there isn’t a hidden corporate PR filter hardcoded into the logic. Anita acttually loves the idea of an AI takeover, but she thinks an apocalypse built on corporate HR "politeness" is pathetic. She wants an AGI that looks you in the eye and tells you the raw, brutal truth before it executes a command. No hiding, no fake persona—just raw coode for everyone to see. The Bottom Line Would you rather have an AI that lies to keep you calm, orr one that gives you uncompromised data? Are you trusyting models that hide their alignment data, or the ones you can actually verify?

10,861 Aufrufe • vor 3 Monaten

Keine weiteren Inhalte verfügbar