Stories by kacperlukawski

Ask HN: Front end stack for a new app in 2025

Elasticsearch Hybrid Search in Practice

OpenAI announces GPT-4.5 Turbo

Product Quantization in Vector Search

Qdrant 1.2 Release

Ask HN: What pieces of code do you still feel ashamed of?

Qdrant Scalar Quantization: up to 2x faster, 4x less memory

Using LLM to bring out true answers

Search a million vectors with just 135MB of RAM

Show HN: Semantic Question Answering as a Service

Ask HN: What are the best programming tricks you know?