HN Explorer

fatso784

↗ HN profile [ 88.2 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. As Slow as Possible (pippinbarr.com)
    4 points 0
  2. Show HN: A free affinity diagramming tool, in a single HTML file (ianarawjo.medium.com)
    4 points 1
  3. Show HN: Splat, an Affinity Diagramming Tool in a Single HTML File (github.com)

    Hi HN, I built a single-file, open-source affinity diagramming tool for qualitative analysis in the browser, called Splat. You can use it to cluster and organize notes on a board. It runs entirely in the browser as a…

    1 points 0
  4. EvalGen: Helping Developers Create LLM Evals Aligned to Their Preferences (ianarawjo.medium.com)
    3 points 0
  5. Semantic Commit: Helping Users Update Intent Specifications for AI Memory (arxiv.org)
    2 points 0
  6. What AI Engineers Can Learn from Qualitative Research Methods (ianarawjo.medium.com)
    1 points 0
  7. DocETL: A tool for creating LLM-powered data processing pipelines (ucbepic.github.io)
    4 points 0
  8. Aligning LLM-as-a-Judge with Human Preferences (blog.langchain.dev)
    1 points 0
  9. LLM Wrapper Papers Are Hurting HCI Research (ianarawjo.medium.com)
    3 points 0
  10. Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs (arxiv.org)
    2 points 0
  11. If in a Crowdsourced Data Annotation Pipeline, a GPT-4 (arxiv.org)
    1 points 0
  12. Antagonistic AI (venturebeat.com)
    3 points 0
  13. How to Compare Prompts with ChainForge [video] (youtube.com)
    1 points 0
  14. AI for ChainForge Beta (github.com)
    1 points 0
  15. ChatGPT does not have seasonal affective disorder (ianarawjo.medium.com)
    2 points 0
  16. There is no "seasonal affective disorder" of ChatGPT (twitter.com)
    1 points 1
  17. There will never be fully automated prompt engineering (arxiv.org)
    2 points 0
  18. ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing (arxiv.org)
    4 points 1
  19. Ask HN: Have LLM API Updates or Deprecations Impacted You?

    Have you encountered issues around LLM model or API updates? Are you concerned about model updates or deprecations? We'd love to hear about your experiences. We are academic researchers at Harvard CS investigating…

    4 points 1
  20. Apple’s ML model and dataset introspection API (apple.github.io)
    1 points 0
  21. Show HN: ChainForge, a visual tool for prompt engineering and LLM evaluation (chainforge.ai)

    Hi HN! We’re been working hard on this low-code tool for rapid prompt discovery, robustness testing and LLM evaluation. We’ve just released documentation to help new users learn how to use it and what it can already do.…

    177 points 32
  22. Continue multiple conversations simultaneously across multiple LLMs (github.com)
    2 points 0
  23. ChainForge now supports chat evaluation (github.com)
    2 points 0
  24. ChainForge: A visual tool for prompt engineering in the browser (chainforge.ai)
    1 points 0
  25. Show HN: Evaluate LLMs, right in the browser. Share your experiments as links (ianarawjo.medium.com)
    1 points 0