Birşeylerin farkına varınca geçmiş hayatımın muhasebesini yapıyorum, bir cahil olarak yaşadığım sonucuna varıyorum, muhtemelen şuanda da bir kaç yıl sonrasının cahiliyim. Cahilim yani
@atarikguney Abi senin yılardır takip ediyorum, sende 3-5 saat danışmanlık alsam 15 sene ileri giderim gibi geliyor hep ama bir türlü nasip olmuyor. ama alacağım
The Deliömerli Roman Bath near Izmir was carved into solid rock over 2,000 years ago, then abandoned for centuries.
And yet the water still runs...
In the first section, the spring is still flowing and still warm, now home to turtles and fish that live in the ancient carved pools.
The mountain kept doing its job long after the people who shaped it were gone.
Some ruins are silent. This one is still quietly working.
We aren't the authors of our thoughts. We're just the user interface. We look at the universe and see a solid reality. The universe looks at us and sees a line of code.
We spend our lives trying to leave a mark on the surface of reality. Oblivious to the fact that our existence is being computed from beneath. We aren't separate individuals. We're just the localized tips of a single, massive mathematical architecture.👇
@AlicanKiraz0 Gelişmiş modeller sadece birkaç firmanın tekelinde uzun süre kalmaz ama hesaplama ve servis maliyet yarattığı için buna öncülük edecek parası olan bağımsız sivil kuruluşlar gerekir
Yani birlik olmak gerekir
📣📣 Meet Qwen-AgentWorld — a native language world model that simulates 7 agent environments (MCP, Search, Terminal, SWE, Web, OS, Android) within a single model. Environment modeling is the training objective from day one, not a post-hoc adaptation.
🤔 LLMs are trained to be better agents — better at acting in environments. But nobody has trained them to model the environments themselves.
🗺️ Our roadmap: investigate how language world modeling can push the boundaries of general agent capabilities, along two routes:
1️⃣ Build a foundation model for environment simulation — outperforming Claude Opus 4.8 and GPT-5.4 on AgentWorldBench
2️⃣ Investigate how world modeling enhances agent training:
🔬 Controllable Sim RL (agentic RL with LWM as environments) surpasses training in real environments
🧠 Learning to predict environments (LWM warm-up) makes agents stronger — remarkably, even without any agent-specific training, this predictive knowledge transfers to agentic tasks with zero fine-tuning
📑 Paper: https://t.co/Jx2l5RKq71
📖 Blog: https://t.co/7tVcKyhsx2
💻 GitHub: https://t.co/B5Lvb1UZCn
🤗 HuggingFace: https://t.co/Kw3QBL1TM5
🧩 ModelScope: https://t.co/YBnGYgMWWI