Halil İbrahim Hatun·Jun 17How AI Agents “Remember” Billions of Things in Milliseconds: Demystifying HNSWIf you’re building LLM pipelines, you already know the dirty secret: Large Language Models have gold-fish memory.
Halil İbrahim Hatun·Jun 12Teacher Forcing vs.If you’ve ever peeked under the hood of ChatGPT, Llama, or any modern Large Language Model (LLM), you’ve probably heard the term…
Halil İbrahim Hatun·Jun 9So Your LLM Falls Apart After 20 Tokens? Yeah, That’s Exposure BiasYou’ve been there.
Halil İbrahim Hatun·Jun 3Stop Wasting VRAM: How TurboQuant Squeezes 128K Context into 3 BitsIf you’ve spent any time serving Large Language Models in production, you know the true enemy isn’t model weights. It’s the KV Cache.
Halil İbrahim Hatun·Jan 3, 2025Evaluate and Debug Your GenAI Model | Part 1 — Introduction to W&BThis tutorial was designed using the Weights & Biases (W&B) Library.
Halil İbrahim Hatun·Sep 13, 2024Exploring DataGemma: An OverviewLLMs are now more resistant to hallucinations
Halil İbrahim Hatun·Apr 12, 2024Cultivating Hospitality Excellence: Transformative Applications for Efficient Staff Management in…Image 1 — Driving Hotel Technology
Halil İbrahim Hatun·Oct 20, 2023Taking a Broad View of the Israel-Hamas ConflictAs many are aware, the conflict between Israel and Hamas has reignited once again. I’ve delved into research and analysis on this critical…
Halil İbrahim Hatun·Aug 30, 2023Graph Neural Networks (GNNs)GCN and GAT Python ImplementationA response icon1A response icon1