HN Explorer

chenxi9649

↗ HN profile [ 85.0 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Agent Skills: One-Shot PySpark from the CLI (lakesail.com)
    22 points 4
  2. Ask HN: How are you teach your kids programming in 2025?

    Hi HN, my nephew is 11, and I'm planning on giving him my old laptop. However, I don't want him to JUST play games 24/7 but for him to do something productive like learning how to code. And I'll meet with him once per…

    8 points 11
  3. Sail: a Rust-Based Spark Replacement (lakesail.com)
    5 points 1
  4. Sail 0.2: Spark replacement in Rust, runs 4x faster, drop-in PySpark compatible (lakesail.com)
    14 points 3
  5. Sail – Unify stream processing, batch processing and compute-intensive workloads (github.com)
    79 points 16
  6. Show HN: Dubbie.com – open-source AI dubbing studio for $0.1/min (github.com)

    Hey HN！ A few months ago I was trying to dub/translate a pretty simple video from English to Chinese for my parents but soon realized that all of the good solutions like Elevenlabs/Rask.ai/Speechify costs around $2/min.…

    2 points 0
  7. Ask HN: Dedicated hardware can 10x inference. Can we do the same with training?

    Recently, we saw Etched that basically implemented transformers in verilog. Before that was Groq, which had some specialized hardware for working with tensors. Both of which can deliver 10-100x faster inference speeds…

    4 points 1
  8. Ask HN: What are some actual use cases of AI Agents right now?

    There are quite a few start ups/OSS working on making LLMs do things on your behalf and not just complete your words. These projects range from small atomic actions to web scrapers to more general ambitious assistants.…

    169 points 153
  9. Ask HN: What's the state of LLM knowledge retrieval in Jan 2024?

    Say I have a huge corpus of unstructured data. What's the most effective way to get a model that can product great answers on that data? Is RAG is still the way to go? Should one fine tune the model on top of that data…

    20 points 2
  10. Ask HN: Is Twitter really as poorly engineered as Elon say it is?

    https://twitter.com/elonmusk/status/1592177471654604800 Elon states - Twitter is doing 1000+ RPCs for a single timeline - Only 20% of Twitter's microservices are needed, and he's turning off a lot of them Can someone…

    17 points 19
  11. Ask HN: What will be the large-scale second-order consequence of AI Art?

    The main use case that comes immediately to mind when using tools like Midjourney/DALL-E/Stable Diffusion is graphic design/stock photos, and most of the discussion surrounds this theme of making art more efficient(like…

    30 points 41