AI Reproducibility Crisis: Why Claims Fail to Verify
A paper reports a new state-of-the-art result. The repo is public. The figures look clean. The conference is top-tier. In…
-
-
LLM Performance Drop: Hosted Models Feel Worse for 3 Reasons
I tried to answer a simple question: is the current LLM performance drop panic actually a real cross-industry regression, or…
-
ARC-AGI-3 Human Baseline Now Means Median Not Outlier
ARC Prize didn’t just tweak a benchmark. The ARC-AGI-3 human baseline now uses a median human run per level instead…
-
Claude Code Cache Bug Turned 5 Minutes Into a Tax
Anthropic’s docs and Boris Cherny’s public clarification describe a split world: main-agent requests typically get a 1-hour cache, while sub-agents…
-
Live AI Video Generation Needs Latency, State, and Deadlines
A lot of live AI video generation demos look the same from the outside: type a prompt, watch moving pixels…
-
Pokémon Go Data Built the Robot Navigation Maps We Use
A red plastic robot rolls past a taco truck in Los Angeles, weaving around a couple arguing over parking. It…
-
Karpathy Autoresearch: 700 Experiments Rewire AI Research
If you tried to copy Karpathy autoresearch this weekend, the first thing you’d hit isn’t the 630 lines of Python….
-
Open-Source Image Geolocation: Netryx & GeoVista Explained
Upload a random street photo, get back GPS coordinates within tens of meters. That’s no longer a closed SaaS demo;…
-
IOS 26 Adoption Isn’t One Number: It’s Three Different Measures
The weird part of the iOS 26 adoption debate is that January headlines argued over third-party numbers like 16% from…
