Submissions from nixiesearch.substack.com

		Show HN: Fine-tuning Qwen3 at home to respond to any prompt with a dad joke (nixiesearch.substack.com)
		10 points by shutty 76 days ago \| past
		Show HN: I benchmarked read latency of AWS S3, S3Express, EBS and Instance store (nixiesearch.substack.com)
		3 points by shutty 3 months ago \| past
		I put a real search engine into a Lambda, so you only pay when you search (nixiesearch.substack.com)
		48 points by shutty 3 months ago \| past \| 13 comments
		We found embedding indexing bottleneck in the least expected place: JSON parsing (nixiesearch.substack.com)
		2 points by shutty 4 months ago \| past
		How [NOT] to Evaluate Your RAG (nixiesearch.substack.com)
		5 points by shutty 8 months ago \| past
		Benchmarking API latency of embedding providers (nixiesearch.substack.com)
		1 point by tanelpoder 11 months ago \| past
		Measuring OpenAI embedding API latency (and why you should always cache it) (nixiesearch.substack.com)
		3 points by shutty 11 months ago \| past
		Nixiesearch: Running Lucene over S3, and why we're building a new search engine (nixiesearch.substack.com)
		128 points by shutty on Oct 10, 2024 \| past \| 76 comments