➡️
继续阅读
-
NVIDIA把供应链专家经验训练进模型，关键不是换一个更大模型
NVIDIA供应链案例表明，专用30B模型经专家决策轨迹训练后，在内部基准上超越更大通用模型。关键在于记录专家决策时的所见、理由与结果，并避免数据泄漏。企...
-
Agent到底比一次大模型调用多了什么？小白从这张流程图看懂
Agent并非更聪明的模型，而是模型外加运行支架，用于管理上下文、工具、环境和会话状态。普通调用适合单轮任务，固定工作流适合步骤明确的场景，Agent适合...
-
AI 智创简报：《大模型账单瘦身专利成簇，中间件的止血生意》
2026年多项专利申请显示，在LLM输入前进行“瘦身”成为趋势，包括日志折叠、子句剪枝、动态截断、工具清单最小化等。Token管控从事后记账前移至喂模型前...
-
Chip Huyen explains how to cut inference costs without new hardware
Last October, the P99 conference — the online gathering for developers focuse...
-
Waymo pulls over, calls cops on riders with a ghost gun
Two people were arrested in San Fransico while riding around in a Waymo robot...
-
“Machine translation is still broken for most of the world’s languages”: Cohere builds non-reasoning for a reason
Enterprise AI company Cohere announced North Small Translate last week, a mix...
