Y Hacker News new | ask | show | jobs

user: shutty created: 2016-06-04 karma: 295 submissions: Benchmarking SlateDB vs. RocksDB 3 points | 0 comments Show HN: MurrDB: A RocksDB-based NVMe/S3 cache for AI inference workloads 1 points | 0 comments Lies, damned lies, and Elastic's benchmarks 4 points | 0 comments Firefox Smart Window 12 points | 1 comments Memento Mori Motivator 1 points | 0 comments 0 points | 0 comments 0 points | 0 comments Accessing LLMs with a Fax [DE] 1 points | 1 comments Fine-tuning Qwen3 at home to respond to any prompt with a dad joke 1 points | 0 comments The Day Our Own Queries DoS'ed Us: Inside Zalando Search 1 points | 0 comments Show HN: Fine-tuning Qwen3 at home to respond to any prompt with a dad joke 10 points | 0 comments Show HN: I benchmarked read latency of AWS S3, S3Express, EBS and Instance store 3 points | 0 comments 0 points | 0 comments I put a real search engine into a Lambda, so you only pay when you search 48 points | 13 comments We found embedding indexing bottleneck in the least expected place: JSON parsing 2 points | 0 comments 0 points | 0 comments Show HN: Nixiesearch, an open-source alternative to Elasticsearch Serverless 2 points | 0 comments Finite State Transducers 1 points | 0 comments 0 points | 0 comments How [NOT] to Evaluate Your RAG 5 points | 0 comments Measuring OpenAI embedding API latency (and why you should always cache it) 3 points | 0 comments Llama.cpp AI Performance with the GeForce RTX 5090 2 points | 0 comments 0 points | 0 comments Show HN: A dataset of all HN submission texts (2006-2024) in Markdown 1 points | 0 comments Hacker News Comments Dataset 2 points | 1 comments Nixiesearch: Running Lucene over S3, and why we're building a new search engine 128 points | 76 comments 0 points | 0 comments 0 points | 0 comments 0 points | 0 comments How to compute LLM embeddings 3X faster with model quantization 2 points | 0 comments