building cool stuff — ex @supabase
Joined June 2020
- Tweets 1,069
- Following 152
- Followers 570
- Likes 3,039
56 Photos and videos
I've been vibecoding a version of #habbo, and I've got to say it's coming along pretty well
This has been done using mostly Codex 5.3 xhigh.
Very impressive.
1
2
158
Misleading. The bigger the model, the longer it’ll take per token. We could be talking about hours per token.
Yes it’s great to split layers, but can’t possibly be used for a real experience or a replacement to GPU.
Don’t believe everything you read!
Jan 29
"I don't have a GPU" is officially dead 🤯
You can now run 70B model on a single 4GB GPU and it even scales up to the colossal Llama 3.1 405B on just 8GB of VRAM.
AirLLM uses "Layer-wise Inference." Instead of loading the whole model, it loads, computes, and flushes one layer at a time
→ No quantization needed by default
→ Supports Llama, Qwen, and Mistral
→ Works on Linux, Windows, and macOS
100% Open Source.
1
114
Qwen-3 TTS is way better than I expected.
After a bit of tweaking, I:
- Ran it locally on an M1 Mac
- Modified Voice-Clone-Studio using @OpenAI Codex
- Cloned a voice in ~5 minutes
The audio is genuinely indistinguishable from reality.
1
189
Voice-Clone-Studio (github.com/FranckyB/Voice-Cl…). Used it as a quick script for a dashboard to upload my voice.
1
66
with Codex, I was able to quickly ignore any CUDA, and just make the script use plain CPU & Metal
55
22 Dec 2025
Remember the game #Habbo? I wonder how far I can get vibecoding it. I’ll post it on this thread.
1
2
87
4 Dec 2025
1/ Why?
Nodra is built on top of @Cloudflare’s Pingora. As a huge fan of the developer tooling by Cloudflare, I wanted to explore if we could create Vercel but for ingress, and that’s what @nodracloud intends to do.
4 Dec 2025
1/ Ingress should be declarative and standardized. We built Nodra to handle the infrastructure complexity so you don't have to.
Waitlist is open: nodra.cloud/waiting
Here is what it does 🧵🧵
1
1
4
523
4 Dec 2025
3/ Open Source:
Nodra’s core components are open source and you can find them in the github organization.
github.com/nodra-cloud
1
1
64
20 Jul 2025
I’m finding out @v0 is great at giving you a first pass of a design, after that, it seems like #Claude does a much better job at refining the v0 project than dealing with v0 itself. Seems like Claude has a better understanding of modern design.
Current process: Create a almost complete design on v0 > Export it > Use Claude to iterate and improve the over all styling.
1
235
6 Jun 2025
There’s a weird UX with v0 and syncing the github repo. @rauchg @v0 .
If the repo is connected and I fork, I need to sync again with the repo. If I’ve already made some changes, syncing would make me loose those changes, so I have to restore the changes before syncing in the current session, and then push the changes. (Very confusing)
It’s also impossible to connect to existent repos.
1
2
349
Andres Pirela acc/Nodra retweeted
2 Dec 2024
today we're releasing @supabase AI assistant v2
it's like cursor for databases. even an Australian can use it ↓↓
69
77
998
143,639
11 Oct 2024
This is top
2
1
584