返回
原文
Yuchen Jin@Yuchenj_UW
63AI 编辑部评分，满分 100
2026-08-08 01:24· 23分钟前
AI 导读

Databricks 数据显示 AI 编程 token 支出正指数级增长。GLM 5.2、Opus 4.8 和 GPT 5.6-Sol 位于“效率前沿”，即每美元质量最优；而 Opus 5.0 相比 4.8 出现成本回退，说明新模型未必更高效。该公司正重投路由、评估及开源与专有模型组合，以优化支出经济学。

At Databricks, AI coding token spend is growing exponentially.

  1. The "efficiency frontier" matters. On Databricks Coding Bench, GLM 5.2, Opus 4.8, and GPT 5.6-Sol sit on that frontier: the best quality per dollar.
  1. We see cost regressions when comparing Opus 5.0 to 4.8. Newer model doesn't always mean more efficient.
  1. Hard budgets are the wrong primitive. Your biggest AI spenders may also be your most AI-leveraged engineers.
  1. There is no best model for every task. Routing, harnesses, evals, and the right mix of open and proprietary models can radically change the economics.

We're investing heavily in all 4, both for ourselves and for our customers.

AnthropicOpenAI推理现象/趋势

来源：Yuchen Jin · x.com

导出 Markdown
返回
63在 X 查看原推
导出 Markdown
Yuchen Jin · @Yuchenj_UW · X·2026-08-08 01:24·23分钟前
AI 导读

Databricks 数据显示 AI 编程 token 支出正指数级增长。GLM 5.2、Opus 4.8 和 GPT 5.6-Sol 位于“效率前沿”，即每美元质量最优；而 Opus 5.0 相比 4.8 出现成本回退，说明新模型未必更高效。该公司正重投路由、评估及开源与专有模型组合，以优化支出经济学。

At Databricks, AI coding token spend is growing exponentially.

  1. The "efficiency frontier" matters. On Databricks Coding Bench, GLM 5.2, Opus 4.8, and GPT 5.6-Sol sit on that frontier: the best quality per dollar.
  1. We see cost regressions when comparing Opus 5.0 to 4.8. Newer model doesn't always mean more efficient.
  1. Hard budgets are the wrong primitive. Your biggest AI spenders may also be your most AI-leveraged engineers.
  1. There is no best model for every task. Routing, harnesses, evals, and the right mix of open and proprietary models can radically change the economics.

We're investing heavily in all 4, both for ourselves and for our customers.

来源：Yuchen Jin· x.com

AnthropicOpenAI推理现象/趋势编码