nullyouraise's recent timeline updates nullyouraise's recent timeline updates |
nullyouraiseV2EX member #606602, joined on 2022-12-13 23:24:30 +08:00Today's activity rank 2773 |
 |
Per nullyouraise's settings, the topics list is hidden |
Deals info, including closed deals, is not hidden
nullyouraise's recent replies
Jul 30 Replied to a topic by C5H12O5 › 程序员 › GitHub Star History 是不是已经完全没法用了 |
现在只有 repo owner 才能访问 star API 了，所以第三方服务必须获取 repo 写权限才能拿
https://www.star-history.com/blog/github-stargazer-api-restriction/
https://www.star-history.com/blog/github-stargazer-api-restriction/
Jul 29 Replied to a topic by weilaa › 问与答 › 公司搞了个中转站，能看到每个人的使用时间，聊天记录会被看到吗？ |
公司提供的 AI 服务，产出都是公司所有，为什么要用公司资源干私事
Jul 21 Replied to a topic by starNew › 程序员 › 汽水音乐的状态栏怎么吸附在 Windows 任务栏的？ |
给你找个有类似功能的开源软件参考一下 https://github.com/zhongyang219/TrafficMonitor
Jul 16 Replied to a topic by Newb1e › 程序员 › 现在不能看别人 github 仓库的 star 的人员列表了吗？ |
是好事吧，除了机器人拉列表给 star 人发垃圾邮件以外，没看到对公共使用者有什么其他正规用途
Jul 14 Replied to a topic by xyz8899 › OpenAI › OpenAI 大善人，又送了一次手动重置卡，已收到！但是要注意一个问题！ |
@ntdll 现在 ChatGPT App 里会给每个重置卡显示过期时间了
Jul 9 Replied to a topic by layxy › OpenAI › codex pro20x 周限砍到 2000 刀以下了 |
@JarvisLee https://openai.com/index/previewing-gpt-5-6-sol/
GPT‑5.6 is priced per 1M tokens across three model sizes: Sol is $5 input / $30 output; Terra is $2.50 input / $15 output; and Luna is $1 input / $6 output. GPT‑5.6 also introduces more predictable prompt caching, including support for explicit cache breakpoints and a 30-minute minimum cache life. For GPT‑5.6 and later models, cache writes are billed at 1.25x the model’s uncached input rate, while cache reads continue to receive the 90% cached-input discount.
GPT‑5.6 is priced per 1M tokens across three model sizes: Sol is $5 input / $30 output; Terra is $2.50 input / $15 output; and Luna is $1 input / $6 output. GPT‑5.6 also introduces more predictable prompt caching, including support for explicit cache breakpoints and a 30-minute minimum cache life. For GPT‑5.6 and later models, cache writes are billed at 1.25x the model’s uncached input rate, while cache reads continue to receive the 90% cached-input discount.
Jul 9 Replied to a topic by layxy › OpenAI › codex pro20x 周限砍到 2000 刀以下了 |
Jul 8 Replied to a topic by layxy › OpenAI › codex pro20x 周限砍到 2000 刀以下了 |
等 GPT-5.6 上线后还会更少，因为 GPT-5.6 的缓存写入开始收费了，按 1.25x 输入 token 计价
Jul 6 Replied to a topic by a815584445 › OpenAI › codex 是真的强 不知道用上 5.6 之后会有多爽 |
@lihanst Opus 基本可以，但是上下文长了会轻微降智； Fable 5 上下文体感是最强的，1M 内随便问，回顾任意内容都能清楚地响应
Select Language