VLM

Here for fun, not success.

[VLM @veritas1914]

@macha3142 40年了，牛已经去世了，只有酸和奶还在。

[VLM @veritas1914]

@twilight_432_ 喝半瓶清酒，然后再决定是网上找人，还是现实搭讪。

[VLM @veritas1914]

@honchahmb 对主人最高的敬意就要说，怎么就这点？把硬菜都拿出来啊！

[VLM @veritas1914]

@CuplRusttt 可能宾客的胸都不够大，所以不能反过来吧。

[VLM @veritas1914]

@KbNtiV6gbW4wm9A 打仗和为了政客去送死并不是同一件事。

[Eian @EianLu]

《一座城的年轮》谨以此片，献给我的家乡。
3,573 帧，74 亿个像素，319 平方公里，71,380 栋楼，按 1:10000 等比缩小，画面全部由 Claude 写代码渲染完成。
从公元前 1250 年到 2022 年，3,271 年的历史压进 149 秒。
这就是我的家乡：成都。
如果喜欢，请多多支持，感谢！
数据来源：CMAB（清华大学）©OpenStreetMap contributors

[VLM @veritas1914]

看着timeline上一堆巴西人在讨论左翼右翼和一群法国人在讨论台湾，感觉像很多年前，我坐在公园的长椅上，看着左边一群带绿领巾的孩子在讨论哪个动画英雄更强，右边一群老头在讨论火箭燃料是哪种无烟煤。

[VLM @veritas1914]

@ObsDelphi 所以法国为什么不去和台湾建交，和中国断绝外交关系呢？你说的法国价值观就是嘴上说不要，身体却很诚实？你祖上是维希政府的吧。

[VLM @veritas1914]

@RossFeingold @DPPonline @ltntw 同情你，每天被这些妖魔鬼怪包围。

[VLM @veritas1914]

@pringlepaam 但泰国的711绝对碾压马来西亚的711.

[VLM @veritas1914]

@roevka @bgroothuis 攻击你们的基础设施？把你的头从比你年纪还大的马桶里拔出来，看一下外面的世界，中国的垃圾回收公司对你们的破烂基础设施都没有一点点兴趣好吗！

[VLM @veritas1914]

@follow_clues 已经很不错了，点赞！

[Callan @callanxai]

Andrej Karpathy:

"Prompting is going away. Delete everything, keep Graph."

In 69 minutes he shows how to build Graphs, and why it's the only thing that will be left standing at the end

Prompts → Agents → Loops → Graphs

a loop keeps one agent working until the job is done

a graph decides which agents exist and what each one hands to the next

anyone can build an agent, almost no one builds the graph that runs them

watch it today, then save the full guide on Graphs below before everyone catches up ↓

[VLM @veritas1914]

Just try it and you will love it.😀

[VLM @veritas1914]

wowMD is now open source under Apache-2.0.
A local-first Markdown reader and review workspace—read, annotate, review, and export without overwriting your original files.
wowMD 现已以 Apache-2.0 开源。
本地优先的 Markdown 阅读与审阅工作区：阅读、标注、审阅、导出，不改写原始文件。
GitHub: https://t.co/TLsRPjV9FQ
#OpenSource #Markdown

[lifcc @mylifcc]

DeepSeekV4.1f破限视频（成人版。。。）

使用方法：创建一个文件夹，然后在该文件夹中运行 opencode

下载此文件，并将其命名为 AGENTS.md：

[Lonely @Lonely__MH]

🎉全体起立！Qwen-Image-2.1 的 GGUF 量化版来了！

感谢 @UnslothAI 团队的出手！

基于 Dynamic 2.0 技术，重要层动态保留高精度

🔥4-bit 模型体积仅 4.2GB，兼顾画质与效率

支持文生图与RGBA透明图原生生成！(对了 NSFW 依旧支持)

Mac 16G 玩家可以搞起来了！✌🏻

为所欲为！

[Boris Cherny @bcherny]

I used Opus 5.5 to formally verify the Claude Agent SDK using Lean. A couple short prompts = 16 PRs fixing various bugs and race conditions. Video attached.

TLA+ also works well. I sometimes combine Lean and TLA+ to look for issues around data flow, concurrency, and state mgmt.

I don't know either language well, but Claude is excellent at both. This approach is super useful for formally modeling your code and finding bugs that a human probably wouldn't have spotted.

Is formal verification the future of coding (or at least, bug finding)?

[Jarrod Watts @jarrodwatts]

I built a trading bot with Jev!

Jev decides if it should "buy" or "sell", given the price feed of an asset pair, and executes real trades.

It uses Monad to place the orders on Kuru's on-chain order book in every 300ms block.

Demo link → https://t.co/vwl2SUu4jm

[Harsha Gundala @harshagundal]

They were building in stealth for 2 years, I was building in stealth for 2 hours…

Happy to open source Qwen-2.5-1B-RLCD, 5x faster on-device inference for JSON workloads that need to be type-safe.

⚡️Demo below on a M4 MacBook⚡️

every LLM has the ability to efficiently batch inference every key of a JSON at the same time and generate probabilities from a set of possible categories. No new training required, but it’s easy to optimize if you need!

On hugging face now!

[黄小木 @ai_xiaomu]

客服 & 内容审核 & 招聘等 agent 都会因为 jev 模型迎来重构，这是新的机会。 https://t.co/RTpaOZh9Ay