The New Stack says agent harnesses—the software around a model—can change coding-agent costs by multiples. Its report uses three benchmarks to examine where extra tokens come from.
The New Stack reports that Aider, Claude Code and OpenClaw ran an identical model, yet token use varied 70-fold. The outlet examines how different agent harnesses can produce dramatically different token usage, making model choice only part of the coding-cost equation.
528
1 post, first seen 3d ago
The New Stack says agent harnesses—the software around a model—can change coding-agent costs by multiples. Its report uses three benchmarks to examine where extra tokens come from.
The New Stack reports that Aider, Claude Code and OpenClaw ran an identical model, yet token use varied 70-fold. The outlet examines how different agent harnesses can produce dramatically different token usage, making model choice only part of the coding-cost equation.
The New Stack@thenewstackThe model isn't the only thing driving AI coding costs. @janakiramm examines how different agent harnesses can produce dramatically different token usage, even when running the same model.
Not enough discussion yet.
No sentiment analysis available yet.
Not enough discussion yet.
No sentiment analysis available yet.
The New Stack@thenewstackThe model isn't the only thing driving AI coding costs. @janakiramm examines how different agent harnesses can produce dramatically different token usage, even when running the same model.
—
Not ranked yet
—
Not ranked yet