Thomas Mark

x.com/i/article/2044…

The last stronghold of coding has just been conquered by AI. In the most recent three Codeforces live competitions, i.e., Round 1087, Round 1088, and Round 1089, GrandCode, our agentic AI system, ranked first in all of them, beating all human participants, including legendary grandmasters. GrandCode is a multi-agent reinforcement learning system designed for competitive programming. It orchestrates a variety of agentic modules (hypothesis proposal, solver, test generator, summarization, etc) and jointly improves them through post-training and online test-time RL. GrandCode is developed based on Qwen. Huge respect to the Qwen @Alibaba_Qwen team for their contributions to the community. It is hard to imagine how quickly AI has advanced in just one year: 1st — GrandCode (March 2026) 8th — Gemini 3.1 Pro (February 2026) 175th — OpenAI o3 (April 2025) We can’t wait to see what happens over the next year.

🎬 Seedance 2.0 is coming. Elser AI is the world's first studio-grade AI film engine and Seedance 2.0 makes it even more powerful. ⚙️ 🎞 True multi-shot storytelling 🎥 Built for real AI filmmaking 🚀 Coming soon. 🎟 Early access available — link in replies 👇 #Seedance2 #ElserAI #AIFilmmaking #AIVideo

KLING 3.0 is LIVE UNLIMITED on Higgsfield. Today marks the MOST advanced AI video model release EVER. Exclusive partnership and Day 0 access. Multi-shot sequences. Macro close-ups through dynamic camera movement. Native audio, real lip-sync and spatial sound. Up to 15 seconds of continuous generation. Get @Kling_ai KLING 3.0 UNLIMITED today with 70% OFF on Premium Plans👇

🚨 memU bot is live. A better alternative to @openclaw (formerly Moltbot / Clawdbot) 👉Get instant access to the memU bot: memu.bot 🕒 A 24/7 proactive assistant memU bot runs continuously on your machine and works as a proactive assistant. It takes action based on your behavior and context — instead of waiting for explicit commands. 🧠 Highly personal, built for you memU bot learns from your long-term usage and memory, and gradually adapts to your work style and preferences. It becomes your assistant — not a generic AI. ⚡ Very easy to use — download and run No complex setup. No configuration. Even non-technical users can simply download and run memU bot. 🔒 Local-first and secure, with no server dependency memU bot runs locally on your device. Your data never needs to be uploaded to public networks or third-party servers. 💸 Lower LLM token cost (more efficient than @openclaw) While supporting always-on and proactive behavior, memU bot is designed to reduce LLM calls and token usage — so it runs cheaper than OpenClaw, without sacrificing performance. 🧠 "Always-on" is the real key to a proactive agent. And memory is what gives it true proactivity. With memory, an agent is no longer generic. It becomes personal — shaped by who you are. This is how a user-intention-driven proactive agent is born: before you even issue a command, it can already anticipate what kind of help you’ll need, based on your past, your habits, your context. 🔮 A 24/7 process that can observe 👀, remember 📝, and act ⚡ — not just wait for prompts. 🤖 memU bot is our attempt at a user-intention-driven proactive agent — one that lives beyond the chat box.

Voice agents are awkward, and everyone notices: You ask a question. The agent thinks. You wait. And wait... Nobody wants this. I'd rather talk to a person. If your model's response time is over 300ms, you won't make it. Unfortunately, most text-to-speech models can't get anywhere close to that. I want you to take a look at the latest model released by @inworld_ai: TTS-1.5. I built a simple voice agent using the model so you can see it in action and test it on your computer. You'll find the repository link below. The latency numbers of this model are wild: • Max model → under 250ms • Mini model → under 130ms That's 4x faster than prior generations and faster than human response times!

We're Einsia.ai — a team of researchers and students who got tired of losing hours to formatting, plotting, debugging, and endless LaTeX errors. So we built an AI academic partner that lives inside your Overleaf. When @OpenAI dropped Prism yesterday, we panicked. Thought we were cooked. Then we ran a head-to-head test. Turns out... we might actually be better? 👀 Don't take our word for it. Here's the receipts — same paper, same prompts, side by side. Einsia.ai goes fully live in 3 days. 👉 einsia.ai to join the waitlist. #EinsiaAI #Overleaf #AcademicTwitter

Inworld TTS-1.5 releases today. The #1 TTS on Artificial Analysis now offers realtime latency under 250ms and optimized expression and stability for user engagement, and costs half a cent per minute. Some voice models are fast, some are expressive, some are affordable. We outperform them all across the board. Production-grade realtime latency: <250ms latency for Max model, <130ms for Mini (P90 first audio) - 4x faster than before. Voice agents now respond before users notice any delay. Engagement-optimized quality: 30% more expressive to serve a wider range of personalities and 40% lower word error rates for fewer hallucinations, word cutoffs, and audio artifacts. Built for consumer-scale: Radically affordable with enhanced multilingual support (15 languages including Hindi) and enhanced voice cloning, now via API. On-prem options now available for enterprises.