HN Explorer

GabrielBianconi

↗ HN profile [ 65.5 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Even (very) noisy LLM evaluators are useful for improving AI agents (tensorzero.com)
    35 points 5
  2. Designing for Agents (twitter.com)
    1 points 0
  3. We're building an automated AI engineer, and it works (tensorzero.com)
    3 points 0
  4. Mitchell Hashimoto on Feature Design [video] (twitter.com)
    3 points 0
  5. Bandits in Your LLM Gateway (tensorzero.com)
    3 points 0
  6. Claude Plays Catan [video] (youtube.com)
    3 points 0
  7. Is OpenAI's Reinforcement Fine-Tuning (RFT) Worth It? (tensorzero.com)
    4 points 0
  8. How Kimi K2 achieves efficient RL parameter updates (moonshotai.github.io)
    3 points 0
  9. Ask HN: How much would it cost to own and operate a personal gTLD?

    I've briefly looked into it before, but the discussion here [1] earlier today made me curious again: How much would it cost to own and operate a personal gTLD? Say, `.gabriel`. ChatGPT claims $250k to start then $100k…

    3 points 2
  10. Deploying DeepSeek on 96 H100 GPUs (lmsys.org)
    285 points 14
  11. Sporks of AGI: why the Real Thing is better than the Next Best Thing (sergeylevine.substack.com)
    3 points 0
  12. We raised $7.3M to build an open-source stack for industrial-grade LLM apps (tensorzero.com)
    1 points 0
  13. Ask HN: How does the Postgres ecosystem compare to Vitess at 1PB+?

    I'm not an expert in databases. The MySQL ecosystem has a mature open-source solution for scaling horizontally with Vitess. The Postgres ecosystem seems to have alternatives like Citus, CockroachDB, etc. Are they…

    4 points 1
  14. Fine-tuned small LLMs can beat large ones with programmatic data curation (tensorzero.com)
    53 points 5
  15. Supervised fine tuning on curated data is reinforcement learning (arxiv.org)
    71 points 9
  16. <syntax-highlight>: custom element that uses the CSS Custom Highlight API (andreruffert.github.io)
    2 points 0
  17. 1 points 0
  18. 1 points 0
  19. From NER to Agents: Does Automated Prompt Engineering Scale to Complex Tasks? (tensorzero.com)
    1 points 0
  20. Can reinforcement learning for LLMs scale beyond math and coding tasks? Probably (arxiv.org)
    6 points 4
  21. Case Study: Automating Code Changelogs at a Large Bank with LLMs (tensorzero.com)
    1 points 0
  22. Show HN: TensorZero – open-source data and learning flywheel for LLMs (github.com)

    Hi HN! We're Gabriel & Viraj, and we're excited to open source TensorZero. To be a little cheeky, TensorZero is an open-source platform that helps LLM applications graduate from API wrappers into defensible AI products.…

    49 points 4
  23. Fast R-CNN – Overview (gabrielbianconi.com)
    1 points 0
  24. R-CNN – Overview (gabrielbianconi.com)
    1 points 0