Research
Multi-agent debate needs a boring data-cleaning cop
Multi-agent debate hurt generation by up to 15.5 points in data cleaning, but a grounded critic rescued detection and repair.
Multi-agent debate needs a boring data-cleaning cop•Unit distance proof moves AI past clever math demos•Vibe coding is loud online and rare in real codebases•AI capability stopped slowing down. It sped up after 2024•The bill for frontier AI is now measured in gigawatts•Your agents are working too hard•The model leaderboard is tightening to a photo finish•
The latest
All articles →
Research
Multi-agent debate needs a boring data-cleaning cop
Multi-agent debate hurt generation by up to 15.5 points in data cleaning, but a grounded critic rescued detection and repair.
Research
Unit distance proof moves AI past clever math demos
The unit distance proof gives OpenAI an AI math win: n^1.014 unit pairs, with humans still doing the verification work.
AI
Vibe coding is loud online and rare in real codebases
Vibe coding dominates AI discourse, but most professional developers still avoid it. The 2025 survey data shows why: the output is almost right too often.
Research
AI capability stopped slowing down. It sped up after 2024
Model capability is improving about 15.5 ECI a year and the rate rose after early 2024. The expected plateau never arrived, which complicates every roadmap built around one.
Business
The bill for frontier AI is now measured in gigawatts
Frontier AI spending has shifted from clever algorithms to power and concrete. A single gigawatt data center now costs about 30 billion dollars to build.
Engineering
Your agents are working too hard
AI agents are not yet mainstream, and the developers who use them report personal speed but little team-wide gain. The fix is teaching agents when to stop.
Browse by section
Follow along
Understand the data & AI story before everyone else.
Every new story, straight to your reader. No newsletter yet, just a clean RSS feed.
Subscribe via RSS