Pinned Tweet
r3.hyperlogue.tech the r3 product site just launched together with the latest r3 v2.2.0.
r3 is like Claude Artifacts, but focusing on viewing & feedback. It works with any agent harness.
I use r3 in almost all my coding sessions. In the last week, agents created 32 artirsions, handled 133 feedback threads with 300+ comments.
The use cases include design review, ui prototype, pre-launch changelong revise, launch video review, code base explanation. It's so versatile and deeply integrated into my agentic workflow.
I'd love to hear what you love about claude artifacts or chatgpt site. We can improve r3 to make the features you love available to everyone on every harness!
r3 is like Claude Artifacts, but focusing on viewing & feedback. It works with any agent harness.
I use r3 in almost all my coding sessions. In the last week, agents created 32 artirsions, handled 133 feedback threads with 300+ comments.
The use cases include design review, ui prototype, pre-launch changelong revise, launch video review, code base explanation. It's so versatile and deeply integrated into my agentic workflow.
I'd love to hear what you love about claude artifacts or chatgpt site. We can improve r3 to make the features you love available to everyone on every harness!
3
0
8
448
Rick Ye retweeted
My iPhone Duo video went viral, so I'm giving away 100 iPhones on X 😛
93,641
100,289
144,108
4,250,138
r3 在最新版里提供了中文界面，文档站也有中文了。喜欢用中文界面的小伙伴可以试一试。
r3 是一个类似 Claude Artifacts 的工具。它专注于评论功能，让你能和 agent 更好地在多轮对话中追踪需要关注的问题。r3 没有做多用户分享或者公开访问之类的功能。
r3 完全在本地运行，并且能适配任何 agent ini 3.8 从英文翻译的。虽然是大型 LLM，翻译出来的结果还是有机翻的味道😂
我自己审阅了一部分，整个审阅的过程也是让 agent 直接写了个 html 放在 r3 里让我提意见，算是 dogfooding 了。
完全用中文来说这些技术词汇的确是有难度。比如 Artifact 这个词我就很难找到合适的翻译，“Review captured changes with the original lines and context intact.” 这句话完全不知道怎么翻译。所以 r3 的中文界面可能会读起来很生硬，希望小伙伴们能多给反馈。
r3 是一个类似 Claude Artifacts 的工具。它专注于评论功能，让你能和 agent 更好地在多轮对话中追踪需要关注的问题。r3 没有做多用户分享或者公开访问之类的功能。
r3 完全在本地运行，并且能适配任何 agent ini 3.8 从英文翻译的。虽然是大型 LLM，翻译出来的结果还是有机翻的味道😂
我自己审阅了一部分，整个审阅的过程也是让 agent 直接写了个 html 放在 r3 里让我提意见，算是 dogfooding 了。
完全用中文来说这些技术词汇的确是有难度。比如 Artifact 这个词我就很难找到合适的翻译，“Review captured changes with the original lines and context intact.” 这句话完全不知道怎么翻译。所以 r3 的中文界面可能会读起来很生硬，希望小伙伴们能多给反馈。
1
0
1
73
Me: seeing the nodejs rce. PANIC. jump up from couch and start to patch my servers.
5 minutes later: wait… we run Bun not node. We are safe.
5 minutes later: wait… does Bun use the same brotli library? Yes?? And it doesn’t have a patch release yet?
Two UNO reverse cards in ten minutes, and I'm back to panicking.
5 minutes later: wait… we run Bun not node. We are safe.
5 minutes later: wait… does Bun use the same brotli library? Yes?? And it doesn’t have a patch release yet?
Two UNO reverse cards in ten minutes, and I'm back to panicking.
1
0
0
79
Amazing news! There must be so much to learn from such a specialized inference stack. They have released their model, kernels and now the inference engine. I wonder what they will open source next? Maybe the training part of the stack?
🚀 Introducing DeepInfer, our in-house inference framework, now fully open source!
Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable.
🔗 github.com/deepseek-ai/De…
1/4
0
0
0
74
Rick Ye retweeted
🚀 Introducing DeepInfer, our in-house inference framework, now fully open source!
Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable.
🔗 github.com/deepseek-ai/De…
1/4
Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable.
🔗 github.com/deepseek-ai/De…
1/4
1,629
4,881
43,034
6,675,956
Rick Ye retweeted
Today, we're open-sourcing 5 Ming-3.0 models across 3 speech families.
- Ming-3.0-tts: 0.5B voice design & paralinguistic cues; Tiny 7.9B A1.3B long-form speech.
- Ming-3.0-audio: Flash 126B A6.5B understanding & tools; Tiny 9.3B A2.7B efficient dialogue.
- Ming-3.0-asr: Tiny 8.6B A2B dialects & context.
- Ming-3.0-tts: 0.5B voice design & paralinguistic cues; Tiny 7.9B A1.3B long-form speech.
- Ming-3.0-audio: Flash 126B A6.5B understanding & tools; Tiny 9.3B A2.7B efficient dialogue.
- Ming-3.0-asr: Tiny 8.6B A2B dialects & context.
88
135
1,368
1,057,036
Rick Ye retweeted
🦆🔫
He convertido un AirPod en un mando para jugar al Duck Hunt.
Lo giras para apuntar y das un toque en el micrófono para disparar.
Sin tocar el ordenador, full vibecodeado por voz al mientras dormía a la bebé 😅
He convertido un AirPod en un mando para jugar al Duck Hunt.
Lo giras para apuntar y das un toque en el micrófono para disparar.
Sin tocar el ordenador, full vibecodeado por voz al mientras dormía a la bebé 😅
98
169
1,845
131,431
Changed borders to green for successful action notifications in captain-miao.
The agent agreed it's better UX. Wondering why didn't it do this on the first pass? Did my prompt over-constrain its taste, or leave too much slack?
How can we get good UI from AI in the first shot?
The agent agreed it's better UX. Wondering why didn't it do this on the first pass? Did my prompt over-constrain its taste, or leave too much slack?
How can we get good UI from AI in the first shot?
0
0
1
87
I've been using Grok Bot and ChatGPT Dots heavily lately, even talking to them in voice mode while I am running. Both have been huge productivity boosters, but each shines in very different ways:
Grok Bot
- Multi-bot workflow: Running multiple bots keeps tasks organized and contexts cleanly isolated.
- Group chat: looks promising in theory, but in practice it gets too chatty without noticeably improving the outcome. I prefer having one bot pinging another bot to transfer context.
- Voice mode: Built for pure efficiency. Well-designed product-wise. It acknowledges my request in a few words, executes, reports back. After hanging up, it drops a text recap with the full transcript available in a few clicks.
ChatGPT Dots
- Long-running tasks: Rock-solid for long tasks. I use it primarily to generate 3D models via Blender. It can reliably work overnight.
- gpt-live: The quality is really really impressive. It genuinely feels like talking to a real person. However I don't find a way to see the transcript, and no recap is given after the call.
How has your experience been with these two products? Which one are you finding more useful day-to-day?
Grok Bot
- Multi-bot workflow: Running multiple bots keeps tasks organized and contexts cleanly isolated.
- Group chat: looks promising in theory, but in practice it gets too chatty without noticeably improving the outcome. I prefer having one bot pinging another bot to transfer context.
- Voice mode: Built for pure efficiency. Well-designed product-wise. It acknowledges my request in a few words, executes, reports back. After hanging up, it drops a text recap with the full transcript available in a few clicks.
ChatGPT Dots
- Long-running tasks: Rock-solid for long tasks. I use it primarily to generate 3D models via Blender. It can reliably work overnight.
- gpt-live: The quality is really really impressive. It genuinely feels like talking to a real person. However I don't find a way to see the transcript, and no recap is given after the call.
How has your experience been with these two products? Which one are you finding more useful day-to-day?
0
0
2
70
Rick Ye retweeted
🚀 DeepSeek-V4.1-Flash-1017 is here!
Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API.
🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, grade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model.
1/4
Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API.
🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, grade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model.
1/4
1,622
4,129
37,134
8,030,666
一个像素风搜打撤 RTS，浏览器里就能玩
我开了两局，还挺有意思的
很明显作者花了不少时间去打磨这个作品
我开了两局，还挺有意思的
很明显作者花了不少时间去打磨这个作品
A solo dev is building a multiplayer extraction RTS with Claude Opus 5.5, plus some help from GPT Astra.
Out of Pixkrieg runs in the browser: take your squad into a raid, find loot, recruit people, and get home alive. Survivors stay for the next run.
His agent workflow:
• He ality bar.
• A worker implements it.
• A reviewer sends back findings.
• They repeat until the result meets that bar.
Project rules, architecture and progress notes live in the repo.
He also built reusable generators for characters, animations and terrain first. With that foundation ready, the first testable prototype took a few weeks.
Would you use the same model to write and review the code?
0
0
2
96
我：是谁泄漏了 .env file
Claude：查到了，是 Codex
Codex：不是我，我什么都不知道。你不对劲，有网络安全风险，已 flag
AI 时代的 office drama，最后受伤的却是老板 🤣
Claude：查到了，是 Codex
Codex：不是我，我什么都不知道。你不对劲，有网络安全风险，已 flag
AI 时代的 office drama，最后受伤的却是老板 🤣
FINALLY found how my key got leaked and got the $90,000 bill from google
Opus 5.5 said codex had PUBLISHED MY ****ING .ENV TO CLOUDFALRE PAGES ‼️
Meanwhile codex couldn't find anything, refused to explain itself and flagged my chat for cybersecurity risk lol
1
0
0
92