Stories by shutty

Lies, damned lies, and Elastic's benchmarks

Firefox Smart Window

Memento Mori Motivator

Accessing LLMs with a Fax [DE]

Fine-tuning Qwen3 at home to respond to any prompt with a dad joke

The Day Our Own Queries DoS'ed Us: Inside Zalando Search

Show HN: Fine-tuning Qwen3 at home to respond to any prompt with a dad joke

Show HN: I benchmarked read latency of AWS S3, S3Express, EBS and Instance store

I put a real search engine into a Lambda, so you only pay when you search

We found embedding indexing bottleneck in the least expected place: JSON parsing

Show HN: Nixiesearch, an open-source alternative to Elasticsearch Serverless

Finite State Transducers

How [NOT] to Evaluate Your RAG

Measuring OpenAI embedding API latency (and why you should always cache it)

Llama.cpp AI Performance with the GeForce RTX 5090

Show HN: A dataset of all HN submission texts (2006-2024) in Markdown

Hacker News Comments Dataset

Nixiesearch: Running Lucene over S3, and why we're building a new search engine

How to compute LLM embeddings 3X faster with model quantization

Show HN: Generating dad jokes with a fine-tuned Mistral-7B

1