Google updates Android Bench with new LLMs, but Gemini still lags behind

Google created a benchmark earlier this year to evaluate how LLMs perform in Android app development, and Android Bench is ...
9to5Google

Google is changing how it judges AI models for Android coding, updates list with Fable 5

Google is changing how it tests AI models for Android coding following new rankings led by Fable 5. Google released the ...

Pragmata god beats the game in less than 80 minutes

When I played through Pragmata back in April, it took me a good 12 hours to beat Capcom's sci-fi shooter. I thought that was ...

I vibe coded a 7-figure tool for my startup. Here are the 4 steps I followed — and how I avoided coding slop.

John Hu left a banking career and his MBA program to build Stan. He and his cofounder went on to vibe code Stanley, an AI tool, in just 14 days.
The Next Web

AI’s hacking skills are outgrowing the tests built to measure them

Frontier AI models are outrunning the benchmarks built to measure their hacking skills, just as a 1 August US deadline for new testing standards looms.