Why AI Confidence Is Mistaken for Intelligence
AI confidence feels like intelligence — but it isn’t. This investigation explains why fluent certainty is a design artefact, not understanding.
Latest
Why "Live Data Access" Does Not Mean Real-Time Learning
Live data access lets AI retrieve information — not learn from it. Here’s why those are fundamentally different processes.
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.
What AI Hallucinations Actually Are — and What They Aren’t
What AI “hallucinations” actually are — and what they aren’t. This explanation clarifies why models confidently produce false outputs, how prediction differs from knowledge, and why hallucinations are a structural limitation rather than a bug or deception.
What Grok actually is - and what it isn't
This explanation separates Grok’s technical reality from the claims surrounding it, clarifying how the system works, why it feels different, and where common misconceptions arise.
How Grok Rumours Spread Faster Than Facts on X
This investigation examines the mechanics, amplification patterns, and platform dynamics that allow claims about Grok to outpace factual verification.
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.
How AI Model Release Timelines Get Fabricated — Inside the Rumour Pipeline
An Investigation into how AI release dates are invented, amplified, and recycled across forums, influencers, and YouTube channels — and why these timelines are almost always wrong.
What “Alignment” Actually Means in AI — And What It Doesn’t
A clear explanation of what AI “alignment” really means, how it works, and why it is often misunderstood as a guarantee of safety or moral behaviour.
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.
How YouTube AI “explainer” channels manufacture fake news
YouTube’s AI “explainer” channels have become a major source of fabricated AI news. This Investigation reveals how these channels turn rumours into viral ‘breaking stories’ using stock footage, AI voices, and zero evidence.
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.
Investigations
Did OpenAI Train on Everyone’s Private Data?
An investigation into what AI companies actually train on, what they don’t, and why the rumour of “they used my private data” continues to spread.
Explanations
What "Model Memory" Actually Means in AI
This explanation clarifies what model memory is, what it is not, and why the confusion persists.
Investigations
The “Sparks of AGI” autopsy: a timeline of strategic breakthroughs
A timeline investigation into how “sparks of AGI” has been used as strategic rhetoric by major AI companies.
Explanations
What training data really means — and why it matters
A clear explanation of what training data is, how AI models learn from it, and why misunderstandings about data lead to exaggerated claims about capability.
Investigations
The benchmark game: how AI leaders use evaluation scores to manage perception
An investigation into how AI companies use benchmarks to shape perception, influence investors, and manage competitive narratives.
Explanations
How chatbots actually work behind the scenes
A clear explanation of how chatbots work behind the scenes by converting text into tokens and predicting the most likely next output.
Explanations
What is an AI model anyway?
A clear explanation of what an AI model actually is, how it works, and what it does and does not understand.
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.