Blogs

🔤 Wordmaze: a one-shot, verifier-graded puzzle for RL Jun 3

🤖 Claude Managed Agents: sharp edges and gotchas Apr 27

✈️ IndiGo: India's Affordable Growth Carrier, by the Numbers Apr 23

💸 A Practical Cost Checklist for Agent and Harness Engineering Apr 21

🔍 Agents Can Reason. They Still Can't Really Search. Mar 17

📏 Bits per byte (BPB) for LLMs: tokenizer-agnostic loss Oct 15

🎨 Creativity Is a Luxury Aug 17

🔀 GPT-5 router: why chat apps will route across models Aug 13

🧠 Instruction Aware Embeddings Jul 8

🔍 How to improve RAG retrieval: recall, precision, and NDCG Mar 8

☁️ AWS Bedrock Converse API: one endpoint for Claude, Llama, and Mistral Jun 13

💾 Database audit fields: created_at, updated_at, created_by, updated_by Apr 17

⚡ KV cache in GPT: how it speeds up transformer inference Feb 12

👨‍💻 LC contest problems summary Nov 28

📝 Hugo commands Nov 28