AnalysisSample
The Index is bounded by its worst dimension, not its best
Coding sits at 81. Embodiment sits at 41 and did not move this quarter. Only one of those numbers tells you when we get there.
8 min
What it means
Analysis
Original work by the Agitology desk. Every piece carries the Index methodology directly, which means it gets revised when the scores underneath it move — and the revision is published rather than quietly applied.
Showing 5 of 5 items.
AnalysisSample
Verification is the bottleneck, and it is not improving
Generation got dramatically cheaper. Checking the output did not. That asymmetry determines where capability gains actually land.
9 min
AnalysisSample
What the widening benchmark-deployment gap actually tells us
Agent benchmarks are saturating while production success rates lag. The gap is not measurement error — it is the measurement working correctly on the wrong thing.
7 min
AnalysisSample
How to read the Index without fooling yourself
A single number about AGI progress is either a useful summary or a false precision machine. Which one depends entirely on how you read it.
6 min
AnalysisSample
Scientific discovery: everything except the part that matters
Autonomous laboratories now close the experimental loop. They have not yet decided what is worth investigating, and that is the whole dimension.
8 min