HN Explorer

typpo

↗ HN profile [ 77.8 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. OpenAI frontier models and Codex are now available on AWS (openai.com)
    370 points 42
  2. How to replicate the Claude Code attack with Promptfoo (promptfoo.dev)
    6 points 0
  3. Questions censored by DeepSeek (promptfoo.dev)
    384 points 256
  4. Llama 3.2 (huggingface.co)
    21 points 1
  5. Automated jailbreaking techniques with DALL-E (promptfoo.dev)
    2 points 1
  6. Show HN: Automated red teaming for your LLM app (promptfoo.dev)

    Hi HN, I built this open-source LLM red teaming tool based on my experience scaling LLMs at a big co to millions of users... and seeing all the bad things people did. How it works: - Uses an unaligned model to create…

    23 points 2
  7. Benchmark Command R vs. GPT/Claude on your own data (promptfoo.dev)
    2 points 0
  8. DBRX vs. Mixtral vs. GPT: create your own benchmark (promptfoo.dev)
    1 points 0
  9. How to benchmark Gemini vs. GPT with your own data (promptfoo.dev)
    1 points 0
  10. A collection of LLM evaluation tools (ianww.com)
    2 points 1
  11. 1 points 0
  12. How to benchmark Llama2 Uncensored vs. GPT-3.5 on your own inputs (promptfoo.dev)
    16 points 0
  13. Benchmark Llama 2 vs. GPT on your own data (promptfoo.dev)
    1 points 0
  14. Show HN: CLI for testing and evaluating LLM prompts and outputs (github.com)

    Hi HN, This project has grown a lot recently and figure it's worth another submission. I use this tool for several LLM-based use cases that have over 100k DAU. It works pretty simply: 1) Create a list of test cases 2)…

    2 points 1
  15. An open-source framework for prompt engineering (ianww.com)
    3 points 0
  16. Show HN: Promptfoo – CLI for testing & improving LLM prompt quality (github.com)
    14 points 5
  17. Show HN: Text-to-Chart – embeddable natural language charts (quickchart.io)
    2 points 1
  18. The Circumnavigators (2017) (qrp-labs.com)
    79 points 37
  19. Show HN: A discord bot that remixes your friends' profile pictures (ianww.com)
    2 points 0
  20. Show HN: Generate SQL Queries from English (querymuse.com)
    5 points 1
  21. Show HN: Open-source document editor for GPT-3 (github.com)

    Hi HN, I built this because I wanted a Google Docs-style editor with GPT-3 tie-in. There are some of these in the wild, but they are expensive. Why is it useful? 1) It's 50x cheaper to run than commercial solutions that…

    1 points 1
  22. A real-time high-quality black hole shader (ebruneton.github.io)
    2 points 0
  23. Show HN: Compare inflation rates across 400 types of items (officialdata.org)
    6 points 2
  24. Zenysis (YC W16) is hiring engineers to improve healthcare across Africa and Asia (zenysis.com)
    1 points 0 job
  25. Show HN: A no-code chart builder (quickchart.io)
    1 points 1