Cheng

57 posts

Cheng banner
Cheng

Cheng

@fancyfrogs

Building @mulerun_ai Virtual world native, BUIDL. previously founder of builtopia, elolab, https://t.co/XsBKMUkA0l and https://t.co/nPWDK5OvKS

GPU Katılım Temmuz 2009
309 Takip Edilen133 Takipçiler
Cheng
Cheng@fancyfrogs·
In SF March 16~18, anyone?
English
2
0
0
151
Cheng retweetledi
MuleRun
MuleRun@mulerun_ai·
🧵 1/2 Will the future of AI Agents be controlled by a few walled gardens? We say no At @mulerun_ai, we're building a truly agnostic marketplace to fight lock-in Our strategy is simple: empower creators with choice and build everything on open protocols Our CPO, @fancyfrogs, details our core philosophy in this new blog post👇 #AI #Agent #MuleRun
MuleRun tweet media
English
2
2
5
825
Cheng
Cheng@fancyfrogs·
Were in the first x space talk but it was ended at the exact 60 minutes. Never knew it was limited🤣
English
3
0
0
430
Cheng
Cheng@fancyfrogs·
@DaemeonDT Which game? (also asked this in discord
English
2
0
0
56
Daejeon
Daejeon@DaemeonDT·
@fancyfrogs Sooo cool I’m thrilled after searching for an AI agent forever. Model companies boast about beating champions or making games, but like many players, I just want an AI to handle sign-ins and daily game tasks. I desperately need an invite code!
English
1
0
0
51
南北西东
南北西东@S_N_W_E·
@op7418 这个思路太对了,把环境和依赖打包,这才是 Agent 该有的样子
中文
1
0
3
1.4K
歸藏(guizang.ai)
歸藏(guizang.ai)@op7418·
试了一下昨天这个海外产品 MuleRun,发现很牛啊。 从理念和效果上看都很厉害,感觉 Agent 产品要有新品类了。 我眼睁睁看这个 AI 帮我打完了星穹铁道的每日任务。 这个最强的核心能力是,每个用户都会有一个完整的虚拟机可以运行 Agent 帮你操作里面的软件,不只是浏览器。 Agent 创建者可以把完成任务的环境建好,用户就能直接用这些自动化的 Agent。 不是 Manus 那种你只能看到有限文件和界面的,你甚至可以自己操作里面的 Windows 电脑,这样想象力就丰富超级多了,Agent 终于拜托了 Office 三件套和网页生成。 他可以帮你自动做游戏的日常,能帮你用 Blender 建模。里面甚至还有帮你自动打崩坏星穹铁道的每日任务的 Agent 。 我亲眼看着他找到游戏的图标启动引导我登录之后开始自己操作角色和界面打对应的日常任务,太省心了,而且这个不死板,你可以指定任务完成的顺序和轮数以及完成哪些任务。 我还用里面的 Blender Agent 让他创建了一个灯塔模型。 里面还有帮你做视频的以及刷评论作图的 Agent,要是有邀请可以试试,很好玩。
歸藏(guizang.ai)@op7418

这个有意思, AI Agent 市场 MuleRun 专业知识被打包成可调用的 AI Agent ,供其他人调用,看起来是走社区逻辑

中文
17
40
253
62.2K
Cheng
Cheng@fancyfrogs·
Anyone tested Claude Code [with] GPT-5 model? 🧐
English
0
0
1
214
Cheng retweetledi
molson 🧠⚙️
molson 🧠⚙️@Molson_Hart·
The White House has put itself and the country in a bad situation but doesn’t realize it yet. Around April 10th China to USA trade shut down. It takes ~30 days for containers to go from China to LA. 45 to Houston by sea, 45 to Chicago by train. 55 to New York by sea. That means that there are no economic effects of what was done on April 10th until about May 10th. Around that time (it’s already started to happen) trucking work is going to dry up. Warehouses will start doing layoffs because no labor is needed to unload containers and some products will be out of stock, reducing the need for shipping labor. All this will start in the Los Angeles area. After about 2 weeks, it’ll start hitting Chicago and Houston. Let’s say the White House, after 3 weeks, changes its mind, on May 31st. “This isn’t working out like we thought it would. Tariffs back to 0.” Let’s say China says “bygones be bygones, we’ll go back to how things were”. Let’s say every factory in China that got screwed by their orders being cancelled says the same thing “no problem, we’ll make and ship”. The problem is, even under the most favorable conditions of China and the factories restarting economic ties as though nothing happened, it will be at least another 30 days before economic activity is revived. And that’s just in LA. In Chicago/Houston, you’ll need to wait another 45 days. New York, at that point, will still be getting containers from before April 10th, they will then have 50 days (May 31 minus April 10) of zero economic activity at the ports, in trucking of Chinese goods, in warehousing. The whole situation is a bit like lockdowns. Once you shut down, it takes a long time to get economic activity back to where it was, if you ever can. And again, this assumes, that China and its factories, which make things you can’t buy elsewhere, will start right back up again as though nothing happened, which is unlikely. It’s almost like we’re speeding towards a brick wall but the driver of the car doesn’t see it yet. By the time he does, it’ll be too late to hit the brakes.
molson 🧠⚙️ tweet media
English
887
6.7K
20.7K
4.1M
Cheng
Cheng@fancyfrogs·
@tingyun97 那是IQ测试网站的广告,不会真有人入局了吧
中文
1
0
0
175
停雲
停雲@tingyun97·
最近看到一个很有意思的话题:其实生活里很多人都是轻微智障,但因为能生活自理,所以没被发现而已……
中文
14
19
130
13.5K
Cheng
Cheng@fancyfrogs·
Wanna get Arcane characters brick sets? popal.ai
Cheng tweet mediaCheng tweet media
English
0
0
1
148
Cheng retweetledi
Andrej Karpathy
Andrej Karpathy@karpathy·
100% Fully Software 2.0 computer. Just a single neural net and no classical software at all. Device inputs (audio video, touch etc) directly feed into a neural net, the outputs of it directly display as audio/video on speaker/screen, that’s it.
English
556
681
7.8K
933.2K
Cheng
Cheng@fancyfrogs·
@peterktodd I don't think the code's out there for the coordinator part?
English
1
0
0
114
Peter Todd
Peter Todd@peterktodd·
It'll be interesting to see if someone else decides to run the coinjoin coordinator. IIUC the code is out there, so nothing is stopping others from taking this up. The coordinator is _not_ trusted.
Wasabi Wallet@wasabiwallet

After years of relentless dedication to improve Bitcoin’s privacy, zkSNACKs, the company pioneering the development of Wasabi Wallet, is shutting down its coinjoin coordination service, effective June 1st, 2024. Blog post announcement link: blog.wasabiwallet.io/zksnacks-is-di…

English
8
11
75
9.7K
Cheng
Cheng@fancyfrogs·
@Kruwed Hey Kruw, curious how you run the coordinator?zkSnacks team did not opensource its code though
English
1
0
0
40
ORE
ORE@OREsupply·
One and only mint address is: oreoN2tQbHXVaZsr3pf66A48miqcBXCDJozganhEJgz Show some love so we can get verified on @JupiterExchange
English
84
70
552
118.5K
Cheng retweetledi
Alex Carlier
Alex Carlier@alexcarliera·
Wow Marigold 🌼 depth estimation works extremely well! 🤯 And the best thing is that the checkpoints and code are fully available for commercial use! Try it out yourself! ⬇️⬇️
Alex Carlier tweet media
English
15
169
1.3K
161.2K