Ryan Anderson @andersryanc

OMG! This skill is so freaking cool! 🔥 It even made the game playable! 🕹️ I'm looking forward to using this to make learning materials for my kid! 👨‍🏫

April @Aprilzz423

4 days ago

Colorfigures skill major update! All 26 Colorfigures are now 3D and see-through 👀 Turn them around, look inside, watch every part do its job. The free open-source Colorfigures skill does this for any object you describe. Now works in Claude, ChatGPT and Gemini, just grab the

33 66 842 30K 737

I asked GPT-6.1 Sol to "Review all of my prompt history and judge me." here's it's top compliments: you’re a product-minded technical generalist whose biggest strength—and recurring liability—is seeing how every small improvement could become something bigger. you keep bringing the conversation back to observable behavior, actual users, and whether the thing works.

Wow, just wow! Can you imagine not having to wait to submit your next prompt? This will allow you to actually get back into that flow state, like when we used to code everything by hand 😂

Fireworks @FireworksAI_HQ

4 days ago

DeepSeek V4.1 Flash 1017 runs at 1,521+ tok/s on Fireworks Ultrafast. Fast enough to ship Tetris in 11 seconds, 7x faster than Claude Opus 5.5. Join the Ultrafast waitlist: bit.ly/3UA0wKq

192 370 6K 1.0M 3K

This is pretty sick! 🔥 Now I just need to buy some smart home gadgets and lights to control with this. 🤣

0xProbability @0xProbabillity

2 days ago

I reverse engineered my smart home. Now it’s on Android too 🤖 Your whole flat as a live 3D model: tap a lamp in 3D and the real one turns on. Phones and tablets, widgets, a Quick Settings tile. Smart Life, Home Assistant, Hue. Free & Open-Source 👇

12 13 250 13K 249

🚨 DO YOU REALIZE WHAT JUST HAPPENED TO THE INTERNET IN 48 HOURS? This is getting OUT OF CONTROL. 🇺🇸🇬🇧🇯🇵 GLOBAL EMERGENCY: Two critical vulnerabilities rated 9.2/10 discovered in PHP, the technology behind nearly 70% of websites. Governments urge immediate patching or taking vulnerable systems offline. ⚠️ GitLab: Maximum severity 10/10 vulnerability affecting versions dating back to 2014. ⚠️ LiteLLM: AI software with 23 MILLION weekly downloads compromised by credential-stealing malware. 🇯🇵 Japan: Up to 26,739 servers potentially affected. Cloud services shut down. 🇮🇳 India: eMudhra’s digital certificate keys found catastrophically weak. One was literally the number FOUR. SBI identifies 3,897 customer records on the dark web. 🤖 AI HACKERS: Over 1,200 websites targeted. More than 100 company sites breached. READ THAT AGAIN. These are separate incidents, but the warning is impossible to ignore. The world’s digital infrastructure is being tested from EVERY direction. And the frightening part? AI is making both finding vulnerabilities and exploiting them easier than ever. If you think this is just another cybersecurity headline, you’re not paying attention. THIS IS A WAKE-UP CALL FOR THE ENTIRE INTERNET. 🚨

Yuto 🇯🇵 @yutokanzakireal

2 months ago

ああ、もし現在の経済秩序の崩壊を、世界的な大危機と重なるまで遅らせることができたら、どれほど都合がいいことだろう。 AI、量子コンピューティング、エネルギー危機。どれでも好きなものを選べばいい。 我々の「同盟国」は、すでに完璧なスケープゴート探しに奔走している。:)

360 2K 10K 4.8M 2K

@bot I guess it can't even file a bug report... although that might be on me and my privacy mode settings. Still seems like it ought to be able to send something with that mode on.

Wow 🙃 @bot has some continuity issues. If you voice chat with it, apparently the context gets lost at the end...

keyboard_arrow_left Previous keyboard_arrow_right Next

This @Starlink account page drives me crazy! Why doesn't the content align with the header? And why are these buttons touching!? And the horizontal spacing is uneven! 😱 Do they have humans working on this or just Grok Bot 😉

Seems like @SpaceX might need some help with their transactional emails! 🤣 Shouldn't these match?

Our job as software engineers has become less about writing code and focused instead on shaping the environment that our agents operate within. Giving them the tools to run more efficiently and with repeatable consistency.

In the age of AI, domain expertise is more important than ever

Another great quote from @dhh The portal to flow was deep immersion into a single problem, see it through to the end... That's not how it works with agents anymore.

@dhh @lexfridman youtu.be/NYFGCESmikA?si…

Love this idea from @dhh on @lexfridman - I totally agree! Agents are both too fast and too slow. Waiting for them feels useless. But if you parallelize them, you can get back to a flow state by constantly doing programming work of making decisions and unblocking them.

Vibecoded a silly little tool that transfers files from your computer to your phone air-gapped using your camera at ~50 Kbps. Nice to have when you're offline or on a plane, or need to send something super duper securely.

Un dev creó transferencia de archivos SIN INTERNET… solo con códigos QR y Claude Un desarrollador quería hacer un reproductor de MP3 web para escapar de los anuncios. Terminó inventando algo mucho más loco: Un sistema air-gapped que pasa archivos de un teléfono a otro
sin WiFi, sin Bluetooth, sin estar en la misma red. ¿Cómo? Mostrando códigos QR que parpadean a toda velocidad en la pantalla. Usó Claude Code y en una sola noche tuvo la prueba de concepto 100% funcional. La IA está haciendo que un solo developer pueda inventar cosas que antes solo se veían en laboratorios. 
El futuro se está construyendo más rápido de lo que creemos.

Amber is a high-level language that compiles to Bash, making shell scripts easier to write and maintain. - Compiles directly to Bash for compatibility with existing environments - Designed specifically for cloud service scripting - Offers high-level abstractions over shell complexity - Supported by documentation and community channels (Discord, IRC, Matrix)

Litestream is a standalone background process that provides disaster recovery for SQLite by replicating changes to S3 or another file. - Runs as a background process with no database modifications - Replicates changes incrementally to S3 or another file - Communicates only through the SQLite API to prevent corruption

🚨 THE "PIRATE BAY" FOR OPEN LLMS IS HERE Hugging Bay is a new verified artifact registry for downloading model weights via torrents and hosted mirrors. But it’s far more than just a file dump. It’s a beautifully structured catalog where every artifact is checked for provenance and license clarity before indexing. You can easily filter across categories: → LLMs & Embeddings (EMB) → Visual (VIS) & Audio (AUD) models → Open-source Agents & Datasets → Apps, Tools, and Evals .. and there are many more feats to explore. They’ve also built in semantic rerank. It means you can search for natural-language queries like "best small commercial embedding model for RAG" and actually get a clean result. really cool stuff. check out the registry below ↓