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.
Latest
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.
Rumours
OpenAI “has a secret internal model that already passed Turing-level AGI tests,” claim leakers
Investigating the rumour that OpenAI has an internal model claimed to have achieved Turing-level reasoning.
Rumours
Meta’s secret “agent swarm” built on LLaMA is already running product teams, say leakers
A review of the rumour that Meta has deployed a secret Llama-based agent swarm in real production environments.
Rumours
Apple’s “secret multimodal AI that will replace iPhones” rumour
Evaluating rumours that Apple is developing a multimodal AI system intended to replace the iPhone in future product lines.
Rumours
Grok is “self-improving” and approaching artificial consciousness, say leakers
Assessing the rumour that Grok is demonstrating self-improvement behaviours and approaching artificial consciousness.
Rumours
LLaMA 4 is “already done and fully AGI-capable,” according to leakers
Reviewing the rumour that Llama 4 has already been completed internally and is capable of AGI-level performance.
Rumours
Claude 3.5 was “secretly trained on 10× more tokens than OpenAI
A review of the rumour that Claude 3.5 was secretly trained on ten times more data than OpenAI’s models.
Rumours
Google Gemini Ultra leaks reveal AGI by Christmas
Assessing the rumour that leaked details about Google Gemini Ultra indicate AGI-level performance by the end of the year.
Rumours
The GPT-5 leak that wasn’t a leak
A breakdown of a widely circulated GPT-5 “leak” that was later shown not to be a genuine disclosure.
About AI Rumour Watch
AI Rumour Watch is an independent editorial project focused on analysing, verifying, and debunking claims about artificial intelligence as they circulate online. The aim is simple: slow claims down, test them against technical reality, and separate what is demonstrably true from what is speculative, exaggerated, or simply wrong. Who “we”