SlopTV: A livestream of AI slop generated from comments, Minimax H3 on 2x5090youtube.com·2 pts·shutty·1
Show HN: Fine-tuning Qwen3 at home to respond to any prompt with a dad jokenixiesearch.substack.com·10 pts·shutty·0
Show HN: I benchmarked read latency of AWS S3, S3Express, EBS and Instance storenixiesearch.substack.com·3 pts·shutty·0
I put a real search engine into a Lambda, so you only pay when you searchnixiesearch.substack.com·48 pts·shutty·13
We found embedding indexing bottleneck in the least expected place: JSON parsingnixiesearch.substack.com·2 pts·shutty·0
Show HN: Nixiesearch, an open-source alternative to Elasticsearch Serverlessgithub.com·2 pts·shutty·0
Measuring OpenAI embedding API latency (and why you should always cache it)nixiesearch.substack.com·3 pts·shutty·0
Nixiesearch: Running Lucene over S3, and why we're building a new search enginenixiesearch.substack.com·128 pts·shutty·76