Rumours
AI Models Secretly Store Everything Users Type, Claim Critics
A common claim suggests AI models secretly store everything users type and can recall it later. There is no evidence this is how modern language models work.
Rumours
Quick-hit analysis of trending AI rumours, leaks, hype cycles, and nonsense.
Rumours
Grok Will Run Fully On-Device in Future Tesla Cars
A widely shared claim suggests Grok will run fully on-device inside Tesla vehicles. There is no evidence this is technically feasible or planned.
Rumours
Is GPT-5 Showing “Near-Human Reasoning”? Claims of Accelerated Training Examined
A circulating rumour claims GPT-5 has shown “near-human reasoning,” prompting OpenAI to accelerate its timeline. There is no evidence supporting these claims.
Rumours
OpenAI secretly trained GPT on private emails, chats, and personal data.
A clear breakdown of why claims about OpenAI training on private emails and messages don’t hold up — and why this rumour keeps returning.
Rumours
Google Gemini Ultra 1.5 leaked to be “conscious,” claims prompt engineer
Investigating the rumour that a prompt engineer reported Gemini Ultra 1.5 behaving in a way described as “conscious.”
Rumours
The EU is “secretly training a shadow-GPT to police all AI models,” claim leakers
Assessing the rumour that the EU is developing a covert “shadow-GPT” to monitor and police AI models across the bloc.
Rumours
IBM is “testing a quantum-enhanced LLM that can predict future market moves,” claim leakers
Evaluating the claim that IBM is experimenting with a quantum-enhanced LLM capable of predicting market movements.
Rumours
IBM is “hiding a prototype model that can predict stock movements with 99% accuracy,” claim leakers
Investigating claims that IBM has an unreleased model allegedly capable of predicting stock movements with high accuracy.
Rumours
DeepSeek’s next model will “solve NP-complete problems in real time,” claim leakers
Assessing the rumour that DeepSeek’s next model will be able to solve NP-complete problems in real time.
Rumours
NVIDIA is “testing a Blackwell-plus prototype that can generate new model weights without training,” claim leakers
Examining the rumour that NVIDIA is testing a Blackwell-Plus prototype capable of autonomously generating new AI models.
Rumours
Meta is “testing a secret LLM that can read minds through keyboard patterns,” claim leakers
Assessing claims that Meta is developing an LLM capable of inferring thoughts from keyboard behaviour and typing patterns.
Rumours
NVIDIA Blackwell 2 will “autonomously train itself to AGI over the weekend,” claim leakers
Evaluating rumours that NVIDIA’s Blackwell 2 hardware could autonomously train itself to AGI-level capability within days.