HN Explorer

kai-dev

↗ HN profile [ 1954 ms ] full profile

No user record in our sample, but kai-dev has activity below (stories or comments). Likely we have partial data — the full bulk-load will fill profiles in.

  1. Ask HN: How big is your LLM compute budget?

    What the title says. I am trying to figure out how much people expect to spend when training their own LLM on their own data from scratch. I’m also wondering if there are techniques you can use to get that cost down…

    4 points 2
  2. Ask HN: Context Window Testing

    I posted previously about this, but I recently build a model that seems to be outperforming most other architectures I've seen. Wondering how to test it's full context window without spending massive amounts of money…

    1 points 0
  3. Rigorous Testing of Novel LLMs

    So, my friend and I built a custom model that is performing 2-3X as good as a comparable decoder only model (~same params, exact same input data etc.) and it's doing this on CodeXGlue. I am currently trying to figure…

    2 points 0
  4. My concerns with modern infra abstractions

    Hello, it’s my first time posting here. I figured this would be a good place to discuss my current concerns about modern infrastructure management abstractions. I am hoping to have a fruitful discuss about how to best…

    1 points 0