Thrilled to partner with @Gradient_HQ in bringing open intelligence to everyone. GLM-4.6 now runs on Gradient’s Parallax, unlocking its power for more users worldwide. Looking forward to what we build together next!
Explore more options from z.ai to help you code faster, smarter, and more reliably. z.ai/subscribe?_cha…
Introducing the newest addition to the @modaicdev DSPy package registry: Codex-Agent by @dronathon Codex-Agent is a module that wraps the OpenAI Codex SDK in DSPy signatures for type-safe, stateful coding agents. Each instance maintains its own conversation thread with full…
Wow! This is music to my ears! “Our goal is process 100M+ research papers and release the full dataset publicly.” Project AELLA could be a game changer in AI assisted open science!
We're introducing Project AELLA, in partnership with @laion_ai & @wyndlabs_ai AELLA is an open-science initiative to make scientific research accessible via structured summaries created by LLMs Available now: - Dataset of 100K summaries - 2 fine-tuned LLMs - 3d visualizer 👇
Very excited that our AlphaProof paper is finally out! It's the final thing I worked on at DeepMind, very satisfying to be able to share the full details now - very fun project and awesome team! julian.ac/blog/2025/11/1…
This is a great move by McConaughey and Caine! Both have iconic voices. Soon, actors will license their avatars also to appear in AI movies. Imagine your favorite actor in 100s of movies every year. Well, okay, maybe that’s a bit too much 😅
Matthew McConaughey and Michael Caine have teamed with AI audio company ElevenLabs to produce AI replications of their famous voices. "To everyone building with voice technology: keep going. You’re helping create a future where we can look up from our screens and connect through…
you can literally play chess with your friends inside @OpenAI ChatGPT now. realtime, multiplayer, so much fun all built with agents SDK here’s how we did it → developers.cloudflare.com/agents/guides/…
You are doing geometry processing, you need precision, performance, and easy compilation on Linux/Mac/Windows ? My fork of the mini-gmp lib is available here: github.com/BrunoLevy/mini… Use it wisely ! (with great power comes great responsibilities...) Image credit: Ed Sheeran
We've gotten super, super deep in the wonderful world of document OCR through the history of @llama_index - and we'd love to share it with you! 🌟 1. There's a lot of benefits to "traditional" methods of reading the PDF binary for fast, cheap parsing. 2. You can use LLMs in the…
We probably shouldn't tell you how to build your own document parsing agents, but we will 😮. AI agents are transforming how we handle messy, real-world documents that break traditional OCR systems. Join our live webinar on December 4th at 9 AM PST where the LlamaParse team…
I goofed around with the new Google ADK Visual Agent Builder over the weekend, and think it has potential. This post goes into great depth on this web-based IDE for building agents, and how to use it. medium.com/@chongcht/buil…
As we mentioned before, happy to introduce Mini Agent, a simple yet powerful CLI demo built with MiniMax M2. 💡 Simple: 14 Python files, 3.3K lines, clean & extensible. ⚙️ Powerful: beautiful CLI, native file/bash tools, auto compaction, MCP integration, and Claude Skill support…
QUESTER: Query Specification for Generative Retrieval Introduces a method where small LLMs generate keyword queries for BM25 retrieval, trained via reinforcement learning to balance effectiveness and efficiency in information retrieval. 📝 arxiv.org/abs/2511.05301
People don't know you can host open source LLM on: > Google Cloud > AWS > Lambda > Together AI > Runpod And even Dockers. So even if you don't have in-house GPUs, you can still self host AI models with best privacy practices.
Anthropic doesn’t want you to know but you can Self-host LLM like Qwen and use it in Claude Code for free
Here's a Linux tip: When you kill a process, you're not "killing" it. You're sending it a signal. It's up to the process to decide what to do. kill <PID> (sends SIGTERM, signal 15): This is the "polite" way. It sends a SIGTERM (Terminate) signal. The process can "catch"…
update: it feels good to be a bit faster than TensorRT, i might explain later (no promises though)
why is triton’s kernel launch cpu overhead so freaking high? the actual kernel takes 10x less execution time than to launch it and i can’t use cuda graphs because the shapes are dynamic.
Cloudflare Workflows, our durable execution engine for running multi-step applications, now supports Python. Here's what this means: cfl.re/3JP9H4d
I’m very interested in seeing how many bits and pieces of finance work we can fully automate with agents. I built a multi-step agentic workflow to automate SEC document understanding👇 Given an SEC filing (10K, 10Q, 8K), use our agent classify module to determine what type it…
Some nice books on statistical distances, goodness of fit, and probability metrics with their applications.
The `try` tool from @tobi has been the biggest positive change to my local workflow in the past year. Nothing comes close. The day I installed and started using it was the last day I lost any of my experiments/plans/repos/docs. Highly recommended! github.com/tobi/try
I've gotten a lot of requests to make a video and screen recording for my MCP Agent Mail project, showing how to set it up and the workflow I use to develop software with it, so I made this: youtube.com/watch?v=68VVcq… Please excuse the lack of production values and my kids' toys!
youtube.com
YouTube
Give your Coding Agents Email and Let Them Team Up to Build Your...
Hilbert geometry of the symmetric positive-definite bicone with applications to extended Gaussians: Degenerate covariance and precision matrices or both on the bicone boundary. arxiv.org/abs/2508.14369
United States Trends
- 1. #AEWDynamite 42K posts
- 2. Epstein 1.43M posts
- 3. #AEWBloodAndGuts 5,355 posts
- 4. #Survivor49 3,407 posts
- 5. Darby 5,027 posts
- 6. Kyle O'Reilly 1,213 posts
- 7. Steph 23.1K posts
- 8. Moxley 2,548 posts
- 9. Hobbs 28.8K posts
- 10. #SistasOnBET 2,149 posts
- 11. Skye Blue 4,021 posts
- 12. Caruso 3,777 posts
- 13. Paul Reed 2,032 posts
- 14. Warriors 47.4K posts
- 15. Draymond 8,604 posts
- 16. Mark Briscoe N/A
- 17. Claudio 24.9K posts
- 18. Knicks 34.3K posts
- 19. Thunder 41K posts
- 20. Hannah Hidalgo 4,604 posts
Something went wrong.
Something went wrong.