Communist Chinese nationals have infiltrated our labs threatening American AI innovation and our national security. I’ve asked @ENERGY to address this problem. https://t.co/5xc0R2QnQF

🚨BREAKING: Marco Rubio is now revoking visas of Chinese students, especially those connected to the CCP. Do you support this? YES or NO? https://t.co/tRMSSlhOkd

I’m not much of a New Year’s Resolutions person, but I would like to eat at Breadbelly as much as possible. https://t.co/i4fQfOYwlA

Fun to see Jell-O shots making a comeback in a much more creative, collagen loving way. https://t.co/GwcqNkoAFK

+1 more

OpenAI running the perfect brand playbook for building trust with consumers - relatable, day in the life of real people - low friction use cases for ChatGPT - helpful inspo, non-threatening companion https://t.co/otSDyIvKF4

Google still has the greatest ad of all time in terms of clearly communicating what the product does and why it's useful. https://t.co/Tm92RUsFch

A study from Kapwing found “21-33% of YouTube’s feed may consist of AI slop or brainrot videos.” https://t.co/LZRJmwnnA6

Puffy vest ✅ Green juice ✅ Seduction ✅✅✅🎰 Amanda Seyfried dancing to Lil Wayne. #TheDropout https://t.co/ximZ9nIqxZ

oh my.. this guy connects Claude to Blender you can do 3D modeling with prompts https://t.co/JuVWBqwhpW

oh my.. this guy connects Claude to Blender you can do 3D modeling with prompts https://t.co/JuVWBqwhpW

View from a window at the Mill Valley Public Library https://t.co/31ysgtt0V6

@gregisenberg I like Shef — homemade meals from people in your neighborhood family recipes made w/ love vs. cloud kitchens that all taste the same https://t.co/5gK6LCo6RF

🧠 Can agent memory scale without losing reasoning? 🔥 We’re excited to share our latest work, SimpleMem, a principled memory framework for LLM agents built around semantic lossless compression. 📉 30× fewer inference tokens 📈 +26.4% avg F1 (vs Mem0) ⚡ 50.2% faster retrieval (vs Mem0) Instead of storing raw interaction history 🗂️ or relying on costly iterative reasoning loops 🔁, SimpleMem treats memory as a structured, evolving representation whose primary objective is 🎯 maximizing information density per token. 📄 Paper: https://t.co/4ZmiXMgzLA 🔗 Code: https://t.co/hhdgvViDwh 📦 Website：https://t.co/B3AhdoTBtS Nice work @JiaqiLiu835914, Yaofeng Su, @richardxp888, @lillianwei423, and great collab. w/ @cihangxie, Zeyu Zheng, @dingmyu

🚀 Supertonic 2 TTS is already here! - Runs entirely on-device - Generates 1 sec of audio in 0.006 sec - Super impressive quality! - 66M params, no cloud, no API calls - 5 languages: EN, KO, ES, PT, FR ⬇️ Demo available on Hugging Face https://t.co/vMUCzpxniM

Weekend project: agent-browser Browser automation CLI for agents → Zero config → Fast Rust CLI → Headed or Headless → Up to 93% less context than Playwright MCP → Compatible with Codex, Claude Code, Gemini, Cursor, Copilot, opencode, and any agent that supports Bash https://t.co/DFl6Fe3aQA

Wow, such a great open-source drop! Put Claude on steroids with 120+ scientific skills spanning maths, biology, chemistry, medicine, engineering, & more 🤯 If you’ve ever wanted Claude to act like a research assistant, this gets very close. Free and open source. Repo in 🧵↓ https://t.co/gWRt3Kzr37

totally blown away by Google Gemini 3 + three.js.. just generated a 3D product interactive app with zero coding.. use hand gesture to rotate, scale, control xyz and lighting of 3D model AI is taking over.. accept or not tutorial with prompts & code below: https://t.co/l3R99B1GEu

Introducing @imagine_dev_ The AI builder with Appwrite Cloud built-in. Build something real. https://t.co/MRzNMdzCcq

Introducing @imagine_dev_ The AI builder with Appwrite Cloud built-in. Build something real. https://t.co/MRzNMdzCcq

Introducing GLM-Image: A new milestone in open-source image generation. GLM-Image uses a hybrid auto-regressive plus diffusion architecture, combining strong global semantic understanding with high fidelity visual detail. It matches mainstream diffusion models in overall quality while excelling at text rendering and knowledge intensive generation. Tech Blog: https://t.co/tVpAVsSmxb Experience it right now: https://t.co/M9UaDtxGoV GitHub: https://t.co/u7HpXQ1WCJ API: https://t.co/SOOzRdErVS Discord: https://t.co/hFcRgVZAqJ Coming soon to https://t.co/DRCwFHQj1P Chat and GLM Coding Plan.

+1 more

Announcing our latest open medical AI models for developers: MedGemma 1.5, which is small enough to run offline & improves performance on 3D imaging (CT & MRI), & MedASR, a speech-to-text model for medical dictation. Both available on Hugging Face + Vertex AI. https://t.co/jPm4UodeAH #MedGemma #HealthAI #GenerativeAI

Glimpse of a world of fully generative interfaces. AI → JSON → UI: https://t.co/BKcvtDky5K https://t.co/QH6ctR1ldA

Glimpse of a world of fully generative interfaces. AI → JSON → UI: https://t.co/BKcvtDky5K https://t.co/QH6ctR1ldA

Today we're open sourcing a technical preview of the GitHub Copilot CLI SDK. Build agents with custom tools in Go, Python, TypeScript, and C#. Built on the same agent loop that powers the Copilot CLI and GitHub Coding Agent. Supports BYOK, and any model. Here is the Copilot CLI driving Excel:

There was a flippening in the last few months: you can run your own LLM inference with rates and performance that match or beat LLM inference APIs. We wrote up the techniques to do so in a new guide, along with code samples. https://t.co/vpNGPZ0vgM https://t.co/wCaWIXwBf6

You can now do reinforcement learning training with 7× longer context and no accuracy loss, via our new batching algorithms. Long reasoning chains in RL are costly, but now we enable you to train gpt-oss with GRPO & reach 380K context on a 192GB GPU. https://t.co/io8OUqGIbn

we're open-sourcing specstory cli we’ve spent a lot of time normalizing agent sessions, and defining a stable contract for ai conversations across tools. and now we are open-sourcing it would love to see what people contribute, build on top of that and build better systems around provenance, memory, and tooling. https://t.co/h8eExqxtf9

🚀 Ling Studio is officially live — the official web platform to interact with Ant Ling models, offering 500,000 free tokens every day to explore, test, and build. In Ling Studio, you’ll experience Ling-1T’s lightning-fast responses, explore Ring-1T for powerful and stable reasoning, and try Ming-flash-omni-Preview to explore image and audio understanding - all in one place. Key features: * Flexible Ling / Ring configuration (parameters + system prompts) * Native tool calling, including web search * API-ready for easy integration into your applications Coming soon: file-based chat, image generation, a growing set of model skills, and more.

AntAngelMed is now open source. 100B parameters. The largest open-source medical LLM to date. Built on the Ling-flash-2.0-base MoE architecture. Ranked #1 among open-source models on OpenAI’s HealthBench. https://t.co/EzNDKdIvQU

even your toaster can see now 🔥 @ultralytics dropped YOLO26 family of models, not only for detection.. 30 models for open vocab detection, segmentation, keypoint detection and more! 🥹 all models <50M params, this demo runs on CPU 🤯 https://t.co/WT8R7zE71V

We’re releasing TranslateGemma, a new family of open translation models with support for 55 languages. 🌐 Available in 4B, 12B, and 27B parameter sizes – they’re designed for efficiency without sacrificing quality. https://t.co/SRJzCOAKyG

Maps codebase architecture from a GitHub URL https://t.co/9Xm6HXgVUW https://t.co/p68HTEdBF5