Ralphilius (@ralphilius) profile picture

Building tiny tools with AI. Maker of @sheetson https://teapawt.net/t.co/NeFkFBjEub https://teapawt.net/t.co/NRmh9KL1CL https://teapawt.net/t.co/RvoiJzMX8s

Vietnam
Joined May 2009
Photo by Ralphilius (@ralphilius)Photo by Ralphilius (@ralphilius)Photo by Ralphilius (@ralphilius)Photo by Ralphilius (@ralphilius)Photo by Ralphilius (@ralphilius)Photo by Ralphilius (@ralphilius)Photo by Ralphilius (@ralphilius)Photo by Ralphilius (@ralphilius)Photo by Ralphilius (@ralphilius)Photo by Ralphilius (@ralphilius)
Time to switch from GLM-5.2 to SWE-2 for freeee
Replying to @cognition
SWE-2 is available today in Devin across Desktop and CLI. We’re making it free for all Pro, Max & Teams subscribers for the next month. Read more about how we trained SWE-2: cognition.com/blog/swe-2
1
57
Gor access to MiMo Desktop program. What are the best use cases for this?
22
Somebody please save him 😬
13
Grok Build on the mobile app is now my favorite on-the-go workflow (after @bot). Building from my phone actually works. One thing I keep wishing for: separate sessions so I don’t burn context tokens every time I switch projects. @grok @spacexai @Baconbrix
1
26
Imagine how much pressure for the team behind Grok 4.7.. You can't go wrong with your schedule 😅
Grok 4.7 comes out in 10 days
1
24
~9x cheaper than Claude, ~7x than 5.6 Sol.. Free in WorkBuddy for two weeks.
🚀 Hy4 preview is here. 770B, 49B active, 1M context. Built for productivity. Open source frontier. Consistent affordable price. Use it. Tell us what breaks. More on Hy blog:hy.tencent.ai/research/hy4-p… HuggingFace:huggingface.co/tencent/Hy4-p… Github:github.com/Tencent-Hunyuan/H…
66
Shipped hill.bid in 10 hours. Stack: @tan_stack. @CloudflareDev Workers. Dodo Payments. Dodo approved me in 8 hours, which is fast until you realize the build was already done. Total time to “you can actually pay”: 18 hours. 10 building. 8 waiting. Should’ve used @freemius. I didn’t need a review. I needed a live checkout.
1
1
58
Interacted with @bot content a few times. Now my feed is flooding with Grok Bot posts 😂
23
Almost 7 days past 🧐
Replying to @congressdj @bot
Making this integration with X much better, ASAP! Also, Grok Bot is now more widely available. teapawt.net/bot/status/20908528813…
24
I was like "poteto poteto poteto, please make Android app" since yesterday 😂
The Grok @Bot team has been cooking! Our Android app is almost ready. Pre-register for the release on the Google Play Store! play.google.com/store/apps/d…
36
Grok @bot is smart, when I just entered "browse Google Search console" without sending yet, a browser session has already started for the agent.
2
4
74
The authentication flow is so aweful..
All SuperGrok and Cursor Pro subscribers now have access to Grok Bot. We're also resetting weekly usage limits for all users. Enjoy!
14
More than $600,000 of tokens cost 🤔
42T tokens of Ox Alpha in 6 days Most used model after DeepSeek Flash's 56 day run Reveal in a few hours
10
So they spent more than $300k token price on marketing. Brilliant or not?
Ox Alpha revealed: @Zai_org’s GLM-5.3-Flash, the first native multimodal model in the GLM-5 series. Ox Alpha was the biggest model ever on OpenRouter, processing over 20 trillion tokens in 6 days. Continue to use the model now: openrouter.ai/z-ai/glm-5.3-f…
9
As expected!!
Time to reveal! Ox Alpha is Zai's GLM Flash 🔥 And it's coming out... tonight!
24
2024: Mac Mini M4 - $599 🥰 2026 Mac Mini M6 - $899 😭
50
I spent 10 hours building hill.bid. ⚡ Not because I knew it would work. I just wanted to see how quickly I could turn an idea into something real. Turns out, the biggest lesson wasn't the product. It was realizing how fast you can launch when you stop overthinking and start building. 🚀
20
I was burning 300M+ tokens a day on Ox Alpha on @OpenRouter, but the rate-limit hit me hard, so I had to switch to Opencode Go. Could have surpassed 1B tokens already
1
131