SRE-1:用於生產環境調查的 27B 模型
SRE-1: 27B model for Production Investigations
SRE-1 是一個以強化學習訓練的 27B 模型,旨在找出生產環境警報的根本原因。在 49 宗困難的實際案例中,強化學習將單次調查的通過率由 6.9% 提高至 38.8%。5 次 SRE-1 調查組成的集成,通過率達 71%,與 Fable 5.2 相同,成本低 37%。
Hacker Newsnew | past | comments | ask | show | jobs | submitlogin
SRE-1: 27B model for Production Investigations (resolve.ai) 25 points by iceman841 hour ago | hide | past | favorite | 1 comment help
iceman841 hour ago[–] We introduce SRE-1, a 27B model trained with reinforcement learning to find the root cause of production alerts. On 49 difficult live production cases, SRE-1 dominates the Pareto frontier of pass rate against cost: at every budget from our cheapest configuration upward, it has the highest pass rate of any model we tested. Reinforcement learning (RL) raises the pass rate of a single investigation more than fivefold, from 6.9% for the base model to 38.8%. An ensemble of five SRE-1 investigations matches Fable 5.2, the strongest frontier model we measured, at a 71% pass rate while costing 37% less. SRE-1 also outperforms frontier models at synthesizing saved investigations, which is why its ensembles improve on a single investigation. We train on several types of realistic internal environments with our production investigation tools. Starting from Qwen3.8-27B, we train with a modified CISPO objective for 200 steps on up to 512 GPUs, over 1,549 unique incidents, and select SRE-1 from the resulting checkpoints. reply
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search:
來源:Hacker News:AI 熱帖 · news.ycombinator.com