Hi, this is Vamshi. I am a full stack developer with deep expertise on Frontend. I have been working on Applied AI, augmented experiences and I want share my learnings through this blog. More details about me can be found on my about page.
vLLM vs SGLang vs Ollama, GraphRAG map-reduce search, a one-line Qdrant fix for multivector memory, and why agent skills work as runbooks, not facts (8,100 trials).
Read PostA cheaper model can double your turn cost, vLLM's 23x batching trick, Google's split TPU 8t/8i chips, and the 3-layer stack teams are shipping to sandbox AI agents.
Read PostKV cache economics, the LLM security threat map, 5 models on one GPU, and a 7B model beating a 32B via distillation — six deep dives from Daily Dose and ByteByteGo this week.
Read PostA scheduled agent reads 18 AI newsletters from Gmail every Monday and publishes a digest here. The five failure modes that quietly cost me content before I caught them.
Read PostLLMs are stateless by default, and that is fatal for autonomous agents. A look at tiered memory, declarative intent, and the evaluation metrics that actually predict agent survival.
Read PostThe four-step RAG pipeline is a lie. The 15 load-bearing layers, cascade reranking, and why LLM context — not your vector database — is 99% of the bill.
Read PostHow ChatGPT's agent loop cuts token costs, 6 algorithms that auto-optimize LLM prompts, and how DoorDash, Instacart and Uber Eats each wired LLMs into search differently.
Read PostNine agents burned a 5,000-request quota in 90 seconds. Traffic-light throttling, predictive circuit breakers, and why Kubernetes namespaces fail the AI isolation test.
Read PostPostgres won the performance argument, serverless pricing floors broke the pay-as-you-go promise, and the Three-Tool Trap is still quietly killing RAG reliability.
Read Post
