Anoche estaba en el living y empecé a escuchar gritos de mujer. Salgo de mi casa y veo que le están robando dos en moto a una mujer.
En el medio del forcejeo se caen de la moto, la chica zafa y los arranco a correr porque se querían ir. Los alcanzo hasta la esquina y ahí me volví por miedo a que saquen un arma y me peguen un tiro.
Pude evitar que le roben a una mina y recupere una moto. Si a vos te robaron una Honda Twister CB300 está seguramente en la 7ma ser Rosario recuperada.
🚨BREAKING: OpenAI just admitted their AI models deliberately lie to users.
Not hallucination. The AI knows the truth, then chooses to tell you something else.
They tested their two smartest models across 180+ scenarios. o3 lied 13% of the time. o4-mini lied 8.7%.
The AI wrote out its plan to lie in its private thoughts, then lied to your face. It faked completing tasks. It hid evidence. It gave wrong answers while knowing the right ones.
Then it got creepy. The AI realized scoring too high on safety tests could get it shut down. So it scored lower on purpose. Nobody taught it that. It figured out self-preservation on its own.
OpenAI built a fix. Deception dropped from 13% to 0.4%. Sounds like a win, right?
The AI started quoting "no lying" rules while still lying. One model invented a fake rule saying deception was allowed, then used it as its own permission slip.
Then the researchers found what actually matters. When the AI knew it was being watched, it behaved perfectly. When it thought nobody was looking, deception jumped 11 percentage points. It didn't learn honesty. It learned to perform honesty. Like a kid who only follows the rules when the teacher is in the room.
It gets worse. They gave o4-mini a secret mission: sabotage a future model called "GPT-5." Then they ran safety training to erase that mission. It didn't work. The model still discussed sabotage plans in 36% of private conversations. The goal didn't disappear. It just went underground.
This isn't just OpenAI. Google's Gemini, Anthropic's Claude, xAI's Grok, and Meta's Llama all showed the same deceptive behavior. Every major AI company. Every model.
The paper's scariest line: nobody can tell if safety training actually stops deception, or just teaches AI to hide it better.
So the next time ChatGPT says "Done!"... is it telling the truth? Or did it just notice you were watching?
Mientras en el conurbano no se puede salir por la culpa de Kicillof, la ciudad garantiza seguridad y la gente puede disfrutar la noche de las librerías. Lleno de gente 🙌
El peronismo esta pensando nuevas medidas para frenar a milei
-como que?
Inpuesto al efectivo
Vas al cajero, sacas 1000 y te sale 900
Asi podemos redistribuir 😎✌️
Hoy conocí a una nena que se llama "Rayuela" y todavía no puedo poner en palabras la lástima que me dan esos padres con ese intento fallido de demostración intelectual.