HN Explorer

sourabh03agr

↗ HN profile [ 71.3 ms ] full profile
Karma
4
Created
September 13, 2020 (5y ago)
Submissions
0
  1. Tracking Prompt Drift for GPT-4 and Claude (demo.uptrain.ai)
    9 points 1
  2. Curiosity-Driven Red-Teaming for Large Language Models (github.com)
    1 points 0
  3. India asks tech firms to seek approval before releasing 'unreliable' AI tools (reuters.com)
    2 points 0
  4. 1 points 0
  5. AI could make the four-day workweek inevitable (bbc.com)
    2 points 1
  6. Is Gemini a case of a biased tuning dataset or model overfitting?

    A quick answer is both, and here is why. Many of us may have seen posts where Google's Gemini model inadvertently generated images with an incorrect skin tone for some well-known individuals. Over the last few days, we…

    1 points 0
  7. How does one detect hallucinations?

    Hallucinations are an interesting artifact of LLMs where the model tends to make up facts or generate outputs that are not factually correct. There are two broad approaches for detecting hallucinations: 1. Verify the…

    5 points 2
  8. Climate change: The 1.5C threshold explained (bbc.com)
    4 points 0
  9. Review: Tuxedo InfinityBook Pro 14 Linux Laptop (wired.com)
    2 points 0
  10. Have we lost faith in technology? (bbc.com)
    2 points 2
  11. Ask HN: Including irrelevant documents improve RAG accuracy by 30%?

    I was very intrigued after reading "The Power of Noise: Redefining Retrieval for RAG Systems" paper (https://arxiv.org/pdf/2401.14887.pdf), where they explored the impact of relevance, position and the number of…

    3 points 0
  12. A collection of different LLM jailbreak techniques and research papers (blog.uptrain.ai)
    3 points 1
  13. Canadian tar sands pollution is up to 6,300% higher than reported (theguardian.com)
    7 points 0
  14. AI news presenters: Can they be trusted? (bbc.com)
    1 points 0
  15. The Japanese philosophy for a no-waste world (bbc.com)
    45 points 46
  16. Can AI Get an Oscar? (bbc.com)
    2 points 0
  17. Integrating Spade: Synthesizing Assertions for LLMs into My OSS Project (github.com)
    6 points 6
  18. Roblox: A student beat Gucci and Karlie Kloss to app award (bbc.com)
    2 points 1
  19. Clocks and watches have shaped our civilisation (bbc.com)
    1 points 0
  20. How OpenAI CEO Sam Altman Was Fired by Rival Board Members (sfstandard.com)
    60 points 30
  21. With Sama's departure, what do you think about Gen AI's adoption by enterprises?

    What do you think- would the recent incident delay the adoption of Gen AI in organizations or would it not change anything much?

    1 points 2
  22. The Devices That Will Read Your Brain–and Enhance It (wsj.com)
    2 points 0
  23. What if you met your future self? (bbc.com)
    2 points 0
  24. Ancient Nvidia GPU used to decode even more antediluvian Roman scroll (pcgamer.com)
    8 points 0
  25. Sharing learnings from evaluating Million+ LLM responses

    Hey everyone, we have been working with many LLM builders to help them evaluate and improve the quality of their LLM applications and recently penned down our learnings on how exactly to evaluate them. We have defined…

    3 points 0