AI News
AI Models Ace the Early Game in Slay the Spire, Then Fall Apart Like Everyone Else
October 12, 2026
SpireBench put 20 language models through full runs of Slay the Spire and found they match average humans but choke against experts, hoarding health instead of spending it and barely learning from past mistakes.
Read more
Rapid-MLX Brings Fast OpenAI and Anthropic APIs to Apple Silicon
October 11, 2026
A new open-source inference server called Rapid-MLX claims to beat Apple’s own mlx-lm at decode speed while adding OpenAI- and Anthropic-compatible APIs built specifically for coding agents on Apple Silicon.
Read more
OpenProblemBench Puts AI Up Against 82 Unsolved Math and Physics Problems
October 10, 2026
A new benchmark drops AI models into 82 genuinely unsolved math and physics problems, with no answer key in sight. GPT-6-Astra topped the field at a 14% judged solve rate, roughly double what full-size open models managed.
Read moreAnalysis
Guides
Cross-Post 5 Platforms in 15 Minutes: The Typefully Workflow
May 22, 2026
Native posting across 5 platforms = 60 minutes. Typefully cross-posting = 15. The 6-step workflow that saves 20 hours/month, and the 4 common mistakes to skip.
