Live data from Hacker News

Viewing profile — pamelafox

pamelafox

HN member
Joined
Tue, Mar 02, 2010, 11:02 PM UTC
HN karma
2,083
Public activity
378 items

About pamelafox

Principal Cloud Advocate @ Microsoft, focusing on Python! Formerly @ UC Berkeley CS, Khan Academy, Coursera, Google. More about me at www.pamelafox.org

Recent public activity

  1. comment
    Comment #47394523

    I think “agent engineering” could refer to the latter, if a distinction needs to be made. I do get what you’re saying, but when I heard the term, I personally understood its meanin…

  2. comment
    Comment #47394512

    I’ve been using the term “agentic coding” more often, because I am always shy to claim that our field rises to the level of the engineers that build bridges and rockets. I’m happy …

  3. comment
    Comment #47044714

    So true! I've also setup automated evaluations using the GitHub Copilot SDK so that I can re-run the same prompt and measure results. I only use that when I want even more confiden…

  4. comment
    Comment #47044313

    This is why I only add information to AGENTS.md when the agent has failed at a task. Then, once I've added the information, I revert the desired changes, re-run the task, and see i…

  5. comment
    Comment #46380029

    I'm on the Python advocacy team at Microsoft, so I've been experimenting a bit with the new framework. It works pretty well, and is comparable to Langchainv1 and Pydantic-AI, but h…

  6. comment
    Comment #45653068

    Yes, AI Search has a new agentic retrieval feature that includes synthetic query generation: https://techcommunity.microsoft.com/blog/azure-ai-foundry-bl... You can customize the m…

  7. comment
    Comment #45649840

    I believe that Azure AI Search currently uses lucene for BM25, hnswlib for vector search, and the Bing re-ranking model for semantic ranking. (So, no, it does not, though features …

  8. comment
    Comment #45649204

    I know :( But I think vector DBs and vector search got so hyped that people thought you could switch entirely over to them. Lots of APIs and frameworks also used "vector store" as …

  9. comment
    Comment #45649184

    Do you mean that you're using the Copilot indexer for Sharepoint docs? https://learn.microsoft.com/en-us/microsoftsearch/semantic-i... AI Search team's been working with the Sharep…

  10. comment
    Comment #45648705

    At Microsoft, that's all baked into Azure AI Search - hybrid search does BM25, vector search, and re-ranking, just with setting booleans to true. It also has a new Agentic retrieva…

  11. comment
    Comment #45619067

    I'd like to know as well, so that I can set up a caterpillar cam.

  12. comment
    Comment #45613720

    Love this! Relatedly, does anyone have a suggestion for an outdoor solar-powered web camera that I could point at the critters in my garden? I'd love to stream a MonarchCam or Mant…

  13. comment
    Comment #45565506

    Ooo bobcats! I live in the bay area near Tilden Park, and I spent a while on iNaturalist trying to figure out where the bobcats hang out, as my 6 year old is very interested in wil…

  14. comment
    Comment #45565477

    I like this point, for people hiring DevRel: "Look in your community. Find users of your product or users of your competitor’s product. " I'm a current DevRel-er myself, and someon…

  15. story
  16. comment
    Comment #45310663

    It was fun! Now we still see Wave-iness in other products: Google Docs uses the Operational Transforms (OT) algorithm for collab editing (or at least it did, last I knew), and non-…

  17. comment
    Comment #45310658

    Hm, I didn't work on the frontend but I don't particularly remember griping..GWT had been around for ~5 years at that point, so it wasn't super new: https://en.wikipedia.org/wiki/G…

  18. comment
    Comment #45298046

    I was on the Wave team! Our servers didn't have enough capacity, we launched too soon. I was managing the developer-facing server for API testing, and I had to slowly let developer…

  19. comment
    Comment #45226073

    How do you determine if the tools access private data? Is it based solely on their tool description (which can be faked) or by trying them in a sandboxed environment or by analyzin…

  20. comment
    Comment #45163467

    I am giving it a go for parenting advice- “My 5 year old is suddenly very germ concious. Doesnt want to touch things, always washing hands. Do deep research, is this normal?” https…

  21. comment
    Comment #45066732

    Both humans and coding agents have their strengths and weaknesses, but I've been appreciating help from coding agents, especially with languages or frameworks where I have less exp…

  22. comment
    Comment #44920378

    When you describe subagents, are those single-tool agents, or are they multi-tool agents with their own ability to reflect and iterate? (i.e. how many actual LLM calls does a subag…

  23. comment
    Comment #44868008

    I ran bulk evaluations on a RAG scenario and wrote-up the results - discovered interesting differences (gpt-5 loves lists, smart quotes, and admitting it doesn't know).

  24. story
  25. comment
    Comment #44852474

    I just ran evaluations of gpt-5 for our RAG scenario and was pleasantly surprised at how often it admitted “ I don’t know” - more than any model I’ve eval’d before. Our prompt does…