What cheaper cache reads change in VulcanBench
A different cache-read rate cuts the estimated Sonnet sweep by 27.44%. The cost-per-success comparison tells a subtler story.
6 min readTechnology / Markets / Incentives
Follow the incentives.
Check the arithmetic.
Notes on technology, markets, and unreasonable ambition. Original analysis, explicit assumptions, and tools you can inspect.
Follow @bozos ↗Featured audit 09 Oct 2026
What cheaper cache reads change in VulcanBench
A small price difference changes the estimated cost. Including failed runs changes how impressive the comparison looks.
Read the analysis →27.44%
Lower estimated sweep cost.
Same recorded usage.
The notebook
All notes →↗
The denominator does the damage
Cheap per attempt can become ordinary per success. A closer look at the Medium-effort comparison.
3 min readA lower price is not a smarter model
What changes when you reprice a fixed workload—and which conclusions the arithmetic cannot support.
3 min readKeep a good question open.
New notes arrive when there’s something worth checking.