Kimi K2.5 的确不错但好像训练的数据有点老？

请不要在回答技术问题时复制粘贴 AI 生成的内容

This topic created in 105 days ago, the information mentioned may be changed or developed.

正准备开个会员，结果 opencode 可以限时免费用了，赶紧试了试，对项目问题的分析很到位，但怎么推理用的数据那么旧？

Let me search for more specific information about libmedia and iOS Safari limitations. Exa Web Search "libmedia AVTranscoder iOS Safari performance file size limitations WASM 2024" Exa Web Search "iPhone Safari file upload size limit blob memory WebAssembly" Thinking: Based on the search results, I can now provide a comprehensive answer about Option 2 (libmedia/AVTranscoder) and its viability on iPhone Safari: Key findings: 1. iOS Safari WASM Memory Issues: - There's a history of Out-Of-Memory (OOM) errors on iOS when using WASM (GitHub issue from 2022 shows "Unhandled Promise Rejection: RangeError: Out of Memory" on iOS 15.2) - ffmpeg.wasm has a 2GB file size limit (GitHub issue #623) - Safari WASM was limited to 2GB until 2021, now supports up to 4GB but with memory fragmentation issues

数据

Safari

wasm

10 replies 2026-02-01 11:24:10 +08:00

vacuitym

Jan 30

一般都是用旧的数据集训练的，感觉国内的和国外的模型还是有差距，你可以试试： https://chat.vacuity.me/#/

huaweii

Jan 30 via Android

kimi 唯二优势，上下文窗口大+相对便宜

dcdlove

Jan 30

@vacuitym 你真是大好人，这么多收费模型免费开放使用

adonishong

Jan 30

简单搜了一下这个问题"iPhone Safari file upload size limit blob memory WebAssembly"

用 google 搜的

搜出来的信息都是什么 20 - 23 年的, 可不就是和 Kimi 说的情况是一样的么 ...

Kimi 那个回答展示的内容很清晰, 不是直接用模型里的知识回答的, 是做了搜索以后回答的, 这和训练数据没什么关系

vacuitym

Jan 30

@dcdlove 我只是送了一些额度，我做不到免费啊！都是我一个个开的官方 api ，家里没矿！