HN Explorer

Joschkabraun

↗ HN profile [ 56.0 ms ] full profile
Karma
7
Created
April 9, 2020 (6y ago)
Submissions
0
  1. 1 points 0
  2. Tactics for multi-step LLM app experimentation (docs.parea.ai)
    1 points 0
  3. A Systematic Workflow to Build Production-Ready LLM Applications (docs.parea.ai)
    3 points 0
  4. Tracking Instructor Validation Errors (python.useinstructor.com)
    1 points 0
  5. 1 points 0
  6. Generate synthetic data for Q&A tasks via instructor in TypeScript (docs.parea.ai)
    2 points 0
  7. Anthropic's Haiku Beats GPT-4 Turbo in Tool Use (docs.parea.ai)
    48 points 15
  8. Ask HN: Who is building on top of OpenAI's Assistants API?

    If so, what is your experience?

    2 points 0
  9. Observability and Testing of OpenAI's Assistants API (docs.parea.ai)
    1 points 0
  10. LLM evals on labeled data (docs.parea.ai)
    1 points 0
  11. Building and Evaluating Evals for Retrieval (docs.parea.ai)
    2 points 0
  12. Reproducible LLM Experimentation with DVC (docs.parea.ai)
    1 points 0
  13. First LLM playground to visualize log-probabilities for OpenAI models (app.parea.ai)
    1 points 0
  14. Logprobs in OpenAI API (platform.openai.com)
    3 points 1
  15. Evaluation metrics for any kind of LLM app: RAG, chat, summarization, etc. (docs.parea.ai)
    1 points 0
  16. Show HN: Reference-free evaluation of LLM-powered chatbots (github.com)

    Hey HN! This an interactive demo with a *somewhat* helpful AI assistant. The goal is to demonstrate a good way to reference-free evaluate interactions between humans and AI assistants. Reference-free means that you do…

    2 points 0
  17. The first playground to experiment with the GPT-4 Vision API (app.parea.ai)
    5 points 1
  18. How has the ChatGPT model changed from March to June? (parea.ai)
    5 points 2
  19. How to Personalize Stable Diffusion for All the Things (jina.ai)
    3 points 0