AI & Machine Learning Threads

@AnatoliKopadze

Article

---...

@hwchase17

Article

<a target="_blank" href="https://www.langchain.com/blog/managed-deep-agents-is-now-in-public-beta" color="blue">Today we’re launching Managed Deep Agents</a> - the easiest way to build, run and deploy production agents. We have a <a target="_blank" href="https://www.langchain.com/blog/managed-deep-a...

@jino_rohit

Article

This blog is my attempt to learn how to profile an llm served using sglang and its in built torch profiler integration that comes out of box. The idea here would be try and understand when I hit sglang serve on my command prompt, can I recognize the CPU side and GPU side events and understand the qu...

@noranta4

Thread

LLMs can hide a text in another text of the same length. I'll explain how, it is very simple, you'll understand before I finish, and smile. That's what I noticed during my #ICLR2026 poster session in Rio! 🇧🇷 Too bad you missed it, but let me remedy now ...

@88n77n

Article

Every demo of this starts with a game character, because a robot knight appearing out of a sentence is easier to sell than a properly lit shampoo bottle....

@mattpocockuk

Thread

llm-wiki has been incredibly useful to me personally, but not in code yet. Folks who are doing this, some questions: - Is it checked into the repo? - What stuff goes in there? - When do things get added? (during planning? implementation?) - How do you avoid mismatches? <span class="quote-card" dat...

@neural_avb

Article

So there are basically two ways people make a LLM "smarter": 1. give it <b>more parameters</b> (a bigger brain), 2. or, give it <b>more compute/data</b> to train on (a longer education). Both work, but both are expensive!...

@Fran_actua

Thread

Todo lo que publico pasa por estos 5 prompts antes de salir. 5 prompts. 5 minutos. Y la diferencia entre un texto que se ignora y un texto que se comparte. 🧵👇(Guárdalo. Tu forma de escribir cambia hoy). ...