This is a submission for the Kaggle Benchmarking Challenge What I Benchmarked BankSafe-Bench: Can AI...
Can AI Be Trusted to Code Financial Software? I Built a Benchmark to Find Out
Related
I hid 6 secret glitches in my agent's video game. They make it easier. Can it find them?
Flash plays a rhythm-runner level from raw pixels. So I hid speedrun-style skips in it: a pad fling over a spike pit, a ghost ship, spike surfing. Nothing on screen gives them away...
Copy the expected, but build what you need.
For the last year I've been working on an app called Glimpse. It's a dictation app and a meeting app,...
AI browsers in 2026: Arc, SigmaOS, Perplexity Comet — are any worth switching?
Arc sits frozen under Atlassian. SigmaOS now charges for features Arc gave away. Comet dropped its...