MedBased (@medbased) 's Twitter Profile
MedBased

@medbased

ID: 1606670845

calendar_today19-07-2013 19:52:59

3,3K Tweet

111 Followers

427 Following

๐Ÿ”ฅ Matt Dancho (Business Science) ๐Ÿ”ฅ (@mdancho84) 's Twitter Profile Photo

OpenAI, Google, and Anthropic just published guides on: โ€ข Prompt engineering โ€ข Building agents โ€ข AI in business โ€ข 601 AI use cases 9 of the best guides you can't miss:

OpenAI, Google, and Anthropic just published guides on:

โ€ข Prompt engineering
โ€ข Building agents
โ€ข AI in business
โ€ข 601 AI use cases

9 of the best guides you can't miss:
Wccftech (@wccftech) 's Twitter Profile Photo

User grabs iBuyPower gaming PC with Ryzen 9800X3Dโ€“RTX 5070 combo, 32 GB RAM, and 2 TB SSD for just $1,000 ๐Ÿ”— wccf.tech/1k202 The Ryzen 9800X3D-RTX 5070 alone costs over $1000 these days.

User grabs iBuyPower gaming PC with Ryzen 9800X3Dโ€“RTX 5070 combo, 32 GB RAM, and 2 TB SSD for just $1,000 ๐Ÿ”— wccf.tech/1k202

The Ryzen 9800X3D-RTX 5070 alone costs over $1000 these days.
GitHub Projects Community (@githubprojects) 's Twitter Profile Photo

If you canโ€™t explain it simply, you donโ€™t understand it. This repo fixes that. Turn any concept into clear, structured explanations that actually make sense. โ€ข Simplifies complex ideas โ€ข Builds real understanding โ€ข Works for code + concep

If you canโ€™t explain it simply, you donโ€™t understand it.

This repo fixes that.

Turn any concept into clear, structured explanations that actually make sense.

โ€ข Simplifies complex ideas
โ€ข Builds real understanding
โ€ข Works for code + concep
AVB (@neural_avb) 's Twitter Profile Photo

After Huggingface, I truly believe Unsloth is most responsible for the democratization of deep learning. Qwen3.5 series of models are GREAT. Even the 2B and 4B ones. 0.8B is immensely finetunable too. Just having access to a readymade RL notebook is so cool. All you need now

Google Research (@googleresearch) 's Twitter Profile Photo

Introducing TurboQuant: Our new compression algorithm that reduces LLM key-value cache memory by at least 6x and delivers up to 8x speedup, all with zero accuracy loss, redefining AI efficiency. Read the blog to learn how it achieves these results: goo.gle/4bsq2qI

Cointelegraph (@cointelegraph) 's Twitter Profile Photo

๐Ÿ‡บ๐Ÿ‡ธ TODAY: The House Financial Services Committee will host a hearing on tokenization and the future of capital markets 10AM EST.

๐Ÿ‡บ๐Ÿ‡ธ TODAY: The House Financial Services Committee will host a hearing on tokenization and the future of capital markets 10AM EST.
NoLimit (@nolimitgains) 's Twitter Profile Photo

๐Ÿšจ UBS halted withdrawals on a $469 million real estate fund for up to 3 years. Translation: โ€œSorry, we donโ€™t have your money.โ€ This is how it starts.

Chong-U (@chongdashu) 's Twitter Profile Photo

Here's a full video walkthrough of generating FF Tactics-style isometric sprites โ†’ Codex โ†’ GPT 5.4 โ†’ GPT Image 1.5 โ†’ Nano Banana 2 โ†’ Veo 3.1 I also made a fal .ai skill to easily switch models for image generation testing. Sharing skills + prompts + resources in reply ๐Ÿ‘‡

Ryan Saavedra (@realsaavedra) 's Twitter Profile Photo

Secretary of State Marco Rubio gives an excellent explanation on why the U.S. needed to strike Iran It's less than 2 minutes and is worth the watch