推理服务的 SLA 工程：SLO、错误预算与容量规划
推理服务向用户承诺「99.9% 可用、P99 延迟 2 秒」——承诺的背后是一套 SLA 工程：SLO 的定义、错误预算的运营、容量规划的科学。本篇拆解推理服务 SLA 的特有指标（TTFT/TPOT 的分位数）、错误预算的纪律、以及容量规划的三步法。
阅读全文 →
全部文章
ARCHIVE 共 443 条ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation
As LLMs are increasingly used for pre-submission self-review, there is growing demand for feedback that not only identif…
GPT-6 让 48 个网页验证码失效了，最聪明的 AI 和最笨的人类相遇了
人类的验证码已经拦不住 AI #欢迎关注爱范儿官方微信公众号：爱范儿（微信号：ifanr），更多精彩内容第一时间为您奉上。 ]
GPT-6 发布后，OpenAI 又自曝「外星思维」，AGI 真的来了？
未来刚才来，它从何而来 #欢迎关注爱范儿官方微信公众号：爱范儿（微信号：ifanr），更多精彩内容第一时间为您奉上。
DeepSeek、千问、智谱轮番登场，PC 厂商终于等到了它们的弹药
AMD 想用电脑把昂贵的 AI Token 账单降下来 #欢迎关注爱范儿官方微信公众号：爱范儿（微信号：ifanr），更多精彩内容第一时间为您奉上。
LatentPort: Beyond KV Cache - Cross-Model Transfer of Recurrent Memory in Hybrid Language Models: A 4B-to-9B Hybrid-State Handoff Without Target Prefix Replay
Can one language model hand its live memory to another without the receiver rereading the context? We demonstrate useful…
没自带 Token，就不配上大学了？
这个月生活费是给外卖，还是给大模型？ #欢迎关注爱范儿官方微信公众号：爱范儿（微信号：ifanr），更多精彩内容第一时间为您奉上。
MLLMs Hallucinate when Information Distribution Drifts in Synergy Heads
Multimodal Large Language Models (MLLMs) often struggle with hallucinations, thus hindering their reliable practical app…
GPT-6 突然全量上线，额度重置再+1，全网实测效果太离谱
GPT-6 Astra 的真正野心，是接管人类的电脑 #欢迎关注爱范儿官方微信公众号：爱范儿（微信号：ifanr），更多精彩内容第一时间为您奉上。
Steering Geometry: Validating Human Value Geometry in LLM Steering Space
As large language models (LLMs) are increasingly deployed in alignment-sensitive contexts, activation steering has emerg…
Online Learning with LLM Experts from Limited Feedback
We study adaptive routing of prompts to large language model (LLM) experts to maximize response quality in an online set…
Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization
Large language models (LLMs) are increasingly used to formulate optimization models from natural-language problem descri…
When Models Edit Too Much: On the Fidelity of Minimal Code Edits
Large language models (LLMs) are increasingly used to edit existing code, but correctness alone is not enough: useful re…