I write code in TypeScript and Rust or AI does it for me

Medellin, Colombia
Opus 5.5 is the Chuck Norris of AI Models.
80
Alex Ramirez retweeted
Alpenglow is now live on devnet, with mainnet coming soon. ⛰️ This whiteboard session with @jacobvcreech and @TheWattenhofer is the ultimate primer on everything you need to know about Alpenglow. Link to the full video below 👇
Made with AI
32
61
293
107,979
My UK visa application is sent. See you there.
A sneak peek behind the curtain of Breakpoint 2026 👀
100
Use AI to augment your thinking, not replace it.
1
2
99
MiMo-V2.6-Pro is a decent model. It gets the job done.
1
101
Alex Ramirez retweeted
Astra (launch day) vs Astra (Today). Same prompt. Today's result looks off. The photo realism is gone. It clearly looks nerfed. GPT-5.6 Sol is unusable for me right now too.
430
330
6,562
1,183,864
I'm rewatching Iron Man tonight. Maybe I'll pick up a few tricks from watching Tony Stark live-code with Astra—I mean, JARVIS.
2
145
I need your input in the app.
1
112
OpenAI gave its latest model the same name as my OpenClaw. I must be some kind of visionary. Astra
Gave my AI Agent Swarm an office. Now I can watch them work in real-time — research, code, design, write — all running in parallel. Managing AI teams from a dashboard hits different. I say the word and Astra, my COO in the Command Center, dispatches them to work. Astra orchestrated the entire workflow and even trimmed the final video for me — without me telling her where the file was located or which file to trim. This was a collaborative effort: 🔍 Sage researched the latest trends and tech for a Virtual AI Agent Office 🎨 Nova designed it 💻 Jax wrote the code 🤖 Astra kept the team in line until I was happy with the results
2
465
Alex Ramirez retweeted
If you’re not reading the code, whether explicitly or through agentic inquiry, one or more of these is true: ○ You’re a beginner ○ Software is throwaway ○ You’re prototyping ○ You have no users / revenue ○ You’re taking on debt & risk ○ Your problems are basic And btw. All of this is fine. But the reality is that models are still not at the “full autonomy” stage yet. They make rookie mistakes, they go down bad architectural paths. I just had the best model in the world add a nonsensical 700ms delay to “settle” something and it told me “you’re right, I was cargo-culting” 🤨 I am on the camp that this need will diminish more and more. Most code is indeed going to be assembly-like. But we also have the global internet and software infrastructure riding on these models and narrative, and we have to respect that.
574
770
8,352
1,326,930
Yes!
We're going to Solana Summer House.
1
171
It was though day for Colombia 🇨🇴
1
1
233
I drink, and Claude knows things.
5
265
Fable 5 is a really good model, but its safeguards are so aggressive that they make it nearly unusable. I’ve seen this message way too often. @AnthropicAI
1
196
Estaré compartiendo con @WayLearnLatam sobre: Arquitectura de Producto sobre Solana para Founders Gracias por la invitación @cristinavlous @SolanaFndn @Solana
3
128
Hey Fable 5, make me a sandwich—make no mistakes.
133
gm ☀️
1
4
156
Colombia 🇨🇴
103
Don't count your chickens before they hatch. #UFCWhiteHouse #UFCFreedom250
294
Alex Ramirez retweeted
the crowd for Qatar vs Switzerland just got an extra show for free anyone want to be the next performance?
Lucky.fun | Crypto Casino
29
12
145
65,095