- 标签:
- AI (69)
- Daily (51)
- Tech Trends (51)
- 技术趋势 (18)
- 推荐系统 (16)
- 日报 (15)
- 周报 (11)
- Agentic Engineering (7)
- 思考 (6)
- 论文 (6)
- Recommendation Systems (6)
- Weekly (6)
- Papers (6)
- 深度学习 (4)
- 工具 (3)
- Harness Engineering (3)
- 推荐 (2)
- 强化学习 (1)
- 思维模型 (1)
- Transformer (1)
- LLM (1)
- 管理 (1)
- 生成式 (1)
2017 年,Ilya Sutskever 读到《Attention Is All You Need》时,立即意识到”这就是我们需要的一切”。OpenAI 随即放弃了 RNN/LSTM 路线,全面转向 Transformer,催生出整个 GPT 系列。Transformer 的并行能力让他们得以实现一直相信的 Scaling 路径。八年后的今天,推荐系统终于走到了同样的路口。 2024 年之前,推荐领域有了 HSTU、TIGER 这样的工作,但大多数团队还在观望。2025 年,我观察到一个明显的转变:大家开始认真地把排序模型 Dense Scaling Up,搞生成式召回和端到端推荐。这很像 2017 年——当时大家忙着把 LR/GBDT/FM 切换到 Deep Model 和双塔,切换过程持续了一两年,之后再没人回头。我的判断是,2026 年将是推荐系统 All-In Transformer 的一年,不改变就落后。
If one word captures AI in 2026-W12, it is "infrastructure" — not the models themselves, but everything required to make them work in the real world. Simon Willison distilled a year's worth of scattered agent engineering lessons into a comprehensive pattern guide. Stratechery declared agents the third paradigm shift for large language models. OpenAI acquired both Promptfoo and Astral within ten days to close environment-management gaps in its coding agent stack. Stripe launched the Machine Payments Protocol (MPP) so agents can spend money autonomously. The entire industry is rapidly shifting from "what can agents do" to "how do agents run reliably, securely, and economically in production."