HN
Paper
All
Show
Ask
Jobs
Top
Today
Last 7 days
Last months
This year
Statistics
All
Show
Ask
Jobs
Top stories
Today
Last 7 days
Last months
This year
Statistics
Stories by
shutty
Lies, damned lies, and Elastic's benchmarks
2 points
shutty
2026-05-12T09:13:46Z
www.gouthamve.dev
Firefox Smart Window
12 points
shutty
2026-04-21T17:45:58Z
www.firefox.com
Memento Mori Motivator
1 points
shutty
2026-02-17T11:47:30Z
mmmotivator.com
Accessing LLMs with a Fax [DE]
1 points
shutty
2026-02-09T10:24:23Z
simple-fax.de
Fine-tuning Qwen3 at home to respond to any prompt with a dad joke
1 points
shutty
2025-12-19T11:50:33Z
medium.com
The Day Our Own Queries DoS'ed Us: Inside Zalando Search
1 points
shutty
2025-12-19T10:06:11Z
engineering.zalando.com
Show HN: Fine-tuning Qwen3 at home to respond to any prompt with a dad joke
10 points
shutty
2025-12-18T15:43:51Z
nixiesearch.substack.com
Show HN: I benchmarked read latency of AWS S3, S3Express, EBS and Instance store
3 points
shutty
2025-12-01T15:58:02Z
nixiesearch.substack.com
I put a real search engine into a Lambda, so you only pay when you search
48 points
shutty
2025-11-24T11:02:51Z
nixiesearch.substack.com
We found embedding indexing bottleneck in the least expected place: JSON parsing
2 points
shutty
2025-11-03T16:34:40Z
nixiesearch.substack.com
Show HN: Nixiesearch, an open-source alternative to Elasticsearch Serverless
2 points
shutty
2025-07-11T16:18:09Z
github.com
Finite State Transducers
1 points
shutty
2025-07-02T16:09:01Z
msfroh.github.io
How [NOT] to Evaluate Your RAG
5 points
shutty
2025-06-30T08:28:33Z
nixiesearch.substack.com
Measuring OpenAI embedding API latency (and why you should always cache it)
3 points
shutty
2025-04-07T13:34:33Z
nixiesearch.substack.com
Llama.cpp AI Performance with the GeForce RTX 5090
2 points
shutty
2025-01-28T22:16:20Z
www.phoronix.com
Show HN: A dataset of all HN submission texts (2006-2024) in Markdown
1 points
shutty
2024-10-13T10:39:12Z
huggingface.co
Hacker News Comments Dataset
2 points
shutty
2024-10-11T15:45:50Z
huggingface.co
Nixiesearch: Running Lucene over S3, and why we're building a new search engine
128 points
shutty
2024-10-10T09:11:26Z
nixiesearch.substack.com
How to compute LLM embeddings 3X faster with model quantization
2 points
shutty
2023-11-17T10:57:57Z
medium.com
Show HN: Generating dad jokes with a fine-tuned Mistral-7B
1 points
shutty
2023-10-16T08:40:07Z
dadjokes.dfdx.me
1