
My deck for the keynote talk at Bosphorus Strait AI 2026 drive.google.com/file/d/1O4q…

Head of Computer Science @ Acıbadem University acibadem.edu.tr/en/ In pursuit of simplicity.

My deck for the keynote talk at Bosphorus Strait AI 2026 drive.google.com/file/d/1O4q…

Soon as a legend, be it a Rock Legend or a Tech Legend, shows tendency towards “We are One ☝️“, a “media lynch” goes underway.
This is why they want him gone

Most teams hand-tune agent prompts until it breaks at scale. This cookbook shows a measured loop: domain judges, expert alignment, and GEPA optimization on MLflow traces. What's inside: • Tool-calling LangGraph agent you can adapt • Domain judges with pass/fail rubrics • Expert alignment via mlflow.log_feedback() + MemAlign • GEPA optimization: 40% → 85% pass rate in the example Run it once, compare baseline vs optimized in the UI. 👉 Check out the cookbook: mlflow.org/cookbook/agent-al…

How would this capability tie in with agent optimization via @gepa_ai ?
🚀 Today we're launching Agent Sandboxes in @pydantic Logfire: a profoundly different kind of sandbox. "The world doesn't need another sandbox" they say. Maybe. Or maybe the world doesn't need another firecracker/gVisor/VM infra-fest. Our Agent Sandboxes are different. They're just an isolated interpreter with cold start times measured in milliseconds, where the code can only call the tools you give it and use the directories you mount. A massive bonus is you can snapshot and resume a REPL weeks later, with the snapshots costing virtually nothing. Programmatic tool calling, solved. Start free, $1000 of free credit to try it in the first month 👇 pydantic.io/launch-agent-san…


Genie has transformed how I work as CTO at Databricks, even more than coding agents. It connects across production data, GitHub, Drive, Slack and the web, and automatically learns from this data (Genie Ontology), so I can ask it to do stuff like: - Tell me how competitors position vs each of our products and which critiques are valid - Find when and why a design decision was made - Find bugs based on production events + code changes - Prototype code changes that would speed up our slowest services in production Really, it can do so much stuff that I would never even bother to ask a person that it totally changes how you work and the size of tasks you can take on directly. Learn more about our latest release of Genie: databricks.com/blog/new-geni…


🇹🇷 Türkiye Cumhuriyeti'nin ilelebet payidar kalması için Gazi Mustafa Kemal Atatürk'ün fikirlerini & duygularını anlamak ve hissetmek gereklidir. Kurtuluş Savaşımızın başkomutanı, Türkiye Cumhuriyeti'nin kurucusu, aziz hatırası kalbimizde ilelebet yaşayacak büyük lider Gazi Mustafa Kemal Atatürk'ü ebediyete intikalinin 88'inci yıl dönümünde saygı, sevgi ve özlemle anıyoruz. 🇹🇷

For important tasks, it is better to form your own initial idea first and then bring in AI: let it expand the scope of your creativity rather than replace its starting point. Otherwise, as we create less and less on our own, we risk gradually weakening our own creative abilities.

Live and discounted on @CheaperInfer
Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges. They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.

Charles Chaplin😂😂

There’s no money in poetry, but then there’s no poetry in money either. —Robert Graves—

That requires knowing what not to build.
The biggest trap with AI coding tools isn't buggy code; it's feature bloat. When you can build anything overnight, saying "no" to 99% of ideas is what keeps a product alive.

“Stop measuring days by degree of productivity and start experiencing them by degree of presence.” ~ Alan Watts

PyCharm 2026.3 is out! 🚀 From agentic coding to deeper framework intelligence, here is what is new in this release: 🤖 JetBrains Air: Run, track, and verify ACP-compatible agents inside your IDE – featuring local, worktree, and cloud execution, plus free agentic coding with Junie Lite 📦 Workspace support: Independent consoles and terminals per subproject, plus seamless member creation and conversion via uv, Hatch, or Poetry ⚡ Python 3.15 lazy imports: Defer module loading to accelerate application startup without losing code insight 🕸️ FastAPI support [Pro]: Interactive dependency graphs for endpoints to trace call chains and flag circular dependencies 🐍 Redesigned Python interpreter widget: Switch and recreate environments organized directly by tool (uv, Poetry, Hatch, conda) 🛡️ Deeper Pydantic support: Real-time Field constraint checks, instant jump-to-definition from field validators, and model configuration completion.

The next decade won't reward tourists. It will reward people who combine audacity with discipline. Who understand that technology cycles come and go, but that building enduring companies requires clarity of purpose and consistency of execution. Venture has always been about backing outliers. That hasn't changed. If anything, it matters more now.