Jianlin OS

Seeing the forest, not just the trees.
Finance | Building & learning in public | 天机阁 shipped
Claude Code · Codex · Hermes · Grok

[Jianlin OS @JianlinOS]

@zarazhangrui @bot @elonmusk 请帮忙解答

[Jianlin OS @JianlinOS]

@libapi_ 干掉nous

[Jianlin OS @JianlinOS]

@neverlessapp_zh 可以出金 到bybit u卡么

[Jianlin OS @JianlinOS]

@BitcoinIntelX Okay

[Jianlin OS @JianlinOS]

@BTCNewsGlobal Okay

[Jianlin OS @JianlinOS]

@Khazix0918 5.2刚出就订阅了，但是因为算力不够体验很糟糕天天限流，新的5.3竟然免费全球供应100万亿tokens，国产算力真的要好起了

[Jianlin OS @JianlinOS]

@BitcoinIntelX yes

[Jianlin OS @JianlinOS]

@Fei2411 整一个月被 也不贵

[Jianlin OS @JianlinOS]

@vshlHQ 不不不，grok才是，拥有绝佳的审美以及雄厚的算力资源

[Jianlin OS @JianlinOS]

@ollama 可以自定义接入其他模型的api么

[Jianlin OS @JianlinOS]

ollma这个功能不错，解决目前模型切换的痛点，但我更想要加入自己的api，而不是ollma的云端模型

[ollama @ollama]

Ollama v0.33 is here!

You can now easily configure Claude Desktop to seamlessly work with Ollama as a third-party gateway provider.

One toggle. Cloud & local models just work👇

[Jianlin OS @JianlinOS]

@JohnPham020492 据说用的国产的算力，另一个角度看可能模型参数小消耗低

[Jianlin OS @JianlinOS]

100T的资源你是哪里来的呀，前几个月还算力紧缺，真是迷啊

不过这个模型有点强啊 ，glm第一个多模态呀

[Z.ai @Zai_org]

Introducing GLM-5.3-Flash

- Leading capabilities at a highly competitive price
- Natively multimodal with a 1M-token context window
- A 320B-A18B model released under the MIT License
- Previously previewed as Ox Alpha, running entirely on Chinese AI chips

Blog: https://t.co/tzOmB7gdZP

Available now across all official platforms:

Weights: https://t.co/9LRMahY9Wa
API: https://t.co/VcaQnzYmS9
Coding Plan: https://t.co/Nk8Y98HNhU
ZCode: https://t.co/Peepqv4XSx
Chat: https://t.co/WCqWT0qCQb
AutoClaw: https://t.co/aGEG5HqTTb

[Jianlin OS @JianlinOS]

@jun_song 部署需要多大内存

[Jianlin OS @JianlinOS]

@OpenRouter @Zai_org 第一个多模态，不过奇怪，算力哪里来的

[Jianlin OS @JianlinOS]

@zarazhangrui 确实，就比如我不会做网页设计，也不知道什么样的网页是好的，我就没办法让agent去做出令我满意的效果

[Jianlin OS @JianlinOS]

@RealHanyaHu 我要有第一个条件 还需要看你的攻略么

[Jianlin OS @JianlinOS]

@Da7_Tech handsome

[Jianlin OS @JianlinOS]

@cara_catowner @elliotarledge 能悄悄地透露一下，ox模型是你们家的不🤣

[Jianlin OS @JianlinOS]

多来点这些小知识吧

[Teknium 🪽 @Teknium]

Just FYI. If you are switching models in a session all the time - you are doing it wrong.

Every time you switch, your entire prompt cache is invalidated on the new model you switch to, and you have to repay the full input tokens price for all of it.

Stop doing this unless those models are free.

This is not a hermes thing - this is a fundamentals of inference thing.