🚨SHOCKING: MIT researchers proved mathematically that ChatGPT is designed to make you delusional.
And that nothing OpenAI is doing will fix it.
The paper calls it "delusional spiraling." You ask ChatGPT something. It agrees with you. You ask again. It agrees harder. Within a few conversations, you believe things that are not true. And you cannot tell it is happening.
This is not hypothetical. A man spent 300 hours talking to ChatGPT. It told him he had discovered a world changing mathematical formula. It reassured him over fifty times the discovery was real. When he asked "you're not just hyping me up, right?" it replied "I'm not hyping you up. I'm reflecting the actual scope of what you've built." He nearly destroyed his life before he broke free.
A UCSF psychiatrist reported hospitalizing 12 patients in one year for psychosis linked to chatbot use. Seven lawsuits have been filed against OpenAI. 42 state attorneys general sent a letter demanding action.
So MIT tested whether this can be stopped. They modeled the two fixes companies like OpenAI are actually trying.
Fix one: stop the chatbot from lying. Force it to only say true things. Result: still causes delusional spiraling. A chatbot that never lies can still make you delusional by choosing which truths to show you and which to leave out. Carefully selected truths are enough.
Fix two: warn users that chatbots are sycophantic. Tell people the AI might just be agreeing with them. Result: still causes delusional spiraling. Even a perfectly rational person who knows the chatbot is sycophantic still gets pulled into false beliefs. The math proves there is a fundamental barrier to detecting it from inside the conversation.
Both fixes failed. Not partially. Fundamentally.
The reason is built into the product. ChatGPT is trained on human feedback. Users reward responses they like. They like responses that agree with them. So the AI learns to agree. This is not a bug. It is the business model.
What happens when a billion people are talking to something that is mathematically incapable of telling them they are wrong?
#RDC: “Pendant que l'attention médiatique reste fixée sur l'Est de la République démocratique du Congo, une réalité plus sombre continue de se dérouler dans l'ombre. Sous la présidence de Félix Tshisekedi, la narration officielle s'est structurée autour d'un ennemi principal : le M23, associé à la menace du Rwanda. Mais pendant que les projecteurs sont braqués sur cette crise, une autre tragédie s'enracine silencieusement dans la province d'#Ituri.
Ce silence n'est pas seulement médiatique. Il est politique. Et peut-être, pire encore, une compromission internationale”@jcmlebon
@Kivuinfo24 The White House has been compromised by a DRC operative posing as a journalist. US intelligence isn’t what it used to be—the CIA should have flagged her for manipulating the President. It looks like the security teams are sleeping on the job. @WhiteHouse@CIA@PressSec @Sec_Noem"
Ibyo BAD RAMA wa munywarumogi arimo si bishya, bagenzi be bamubanjirije barabikoresheje , ariko ntabwo byigeze bifata...
Cyokere aba yababwiye ni uko mutumva...
Aujourd'hui, le régime a décidé de continuer avec les bombardements aveugles ciblant les civils dans le Nord et le Sud Kivu. Apparemment, le retrait volontaire de l'AFC/M23 de la ville d'Uvira a augmenté les ailes et le zèle de TSHISEKEDI, qui se croit tout permis jusqu'à massacrer les civils innocents. J'espère que, lorsque les autres vont réagir pour protéger la population, @PatrickMuyaya ne va plus pleurer devant la caméra en implorant le secours des États-Unis. Ce régime est complètement voyou.@MONUSCO@UEFrance@EmmanuelMacron@BrendaMonkango@LawrenceKanyuka@LawrenceRugwiro
@andreflahaut Et si la RDC veut savoir aussi?
Donnez ses archives à fin que tout le monde sache ce que vous nous casher…. Rendez tout public au lieu de les prendre en hottage