Blog

Intelligence

Models, reasoning, multimodal systems, and the capabilities changing what machines can do.

OpenAI vs. the Truth: What Is Really Happening With GPT-6 Astra?

OpenAI says GPT-6 Astra starts the AGI era. Independent testers say 62.7, not 99.9, and a tie on the intelligence index. The claim that matters is about office work and zero-days.

Why You Should Be Skeptical of OpenAI's 99.9 Percent AGI Score

OpenAI says GPT-6 Astra scores 99.9 percent on ARC-AGI-3. The people who run the test got 62.7. The gap is the harness, and here is what that word means.

AI Cracked a Millennium Math Problem? The Fight Over the Claim

OpenAI says a model helped crack a Navier-Stokes problem, one of math's hardest. The claim is disputed, over credit and over cheating. Here is what is known.

The $6-an-Hour Engineer? GPT-6 Astra, Explained

OpenAI's GPT-6 Astra is its best model yet for software engineering. The viral 'six dollars an hour' figure is an independent estimate, not OpenAI's price. Here is what is real.

Did Anthropic Just Have Twins? Claude Fable 5.1 and Mythos 5.1

Anthropic shipped two Claude 5.1 models that share one brain. Fable is for everyone; Mythos is gated. Here is why the split exists and what it means for you.

The Screen Is the Software: Runway Solaris Explained

Runway's Solaris generates the interface itself, frame by frame, in real time. No DOM, no CSS, no JavaScript. Here is how an Interface World Model works.