Live data from Hacker News

Viewing profile — barefeg

barefeg

HN member
Joined
Sat, Dec 19, 2020, 11:07 AM UTC
HN karma
180
Public activity
202 items

About barefeg

No profile information was provided.

Recent public activity

  1. comment
    Comment #43896977

    For some time, authentication was not part of the MCP. Now it’s there https://modelcontextprotocol.io/specification/2025-03-26/bas... so I’m wondering what is being addressed in Kl…

  2. comment
    Comment #42444670

    Thanks for sharing your blogpost. We had a similar journey. I installed and tried both Langfuse and Phoenix and ended up choosing Langfuse due to some versioning conflicts on the p…

  3. comment
    Comment #41267607

    He hinted at wanted to be convinced to work at the company. It seems as if he wants people to just know he’s good and people offer him the job instead of applying for it. It’s a bi…

  4. comment
    Comment #40392468

    From this interview https://youtu.be/Nlkk3glap_U?feature=shared it seemed Anthropic was focusing more on those topics rather than winning the race. He hinted at being “forced” by t…

  5. comment
    Comment #40195094

    I was confused for a bit but there is no relation to https://haystack.deepset.ai/

  6. story
  7. comment
    Comment #39843981

    This technique had a very recent resurgence via https://txt.cohere.com/int8-binary-embeddings/ . Hugging face also covered the technique here https://huggingface.co/blog/embedding-…

  8. comment
    Comment #38581871

    Could you give more details/resources on the distributed in cluster buildkit cache?

  9. comment
    Comment #38420642

    Have you tried the arc browser? It embraces having lots of open tabs and organize them as you wish (or not) https://arc.net/

  10. comment
    Comment #38319069

    Do you need to have the same number of positive and negatives? Is there any meaning of pairing a positive an a negative in the triplet?

  11. comment
    Comment #38247615

    Out of curiosity, how does it compare to YouTube’s own generated transcripts?

  12. comment
    Comment #38061246

    I wish they had cut all benefits from tier 3 companies only^[1] while leaving other tiers intact. Big tech salaries in Europe are already so much higher in comparison, that it woul…

  13. comment
    Comment #38061150

    Are there any disadvantages of using let’s encrypt for certs? It would solve the renewal issue.

  14. story
  15. comment
    Comment #37965183

    We started with something like this as well. The problem is that the savings and disposable income will also be proportional. If the difference in salaries is large then it could s…

  16. comment
    Comment #37959235

    Does splitting here mean each person pays half of the price of the shared item? If so that puts more pressure on the lower earner. One approach would be to put both incomes in a bi…

  17. comment
    Comment #37848142

    FastAPI which is a python framework

  18. comment
    Comment #37835743

    Maybe I didn’t explain the process correctly, we do generate the spec first, it’s just that the tool we use for creating the spec is the code that will later contain the implementa…

  19. comment
    Comment #37835588

    Thanks. I missed this part https://openapistack.co/docs/openapi-backend/typescript/ so the types are generated for the backend to use. We’ve used API first approach before, but it …

  20. comment
    Comment #37835424

    How do you make sure that the spec is in sync with the implementation?

  21. comment
    Comment #37396469

    Thanks! It does clarify the difference.

  22. comment
    Comment #37396330

    You can try the 3 methods: keyword, knn, and hybrid on a collection in the AI domain here https://search.zeta-alpha.com/ . YMMV sometimes knn has more interesting results, sometime…

  23. comment
    Comment #37312818

    I feel like small formulas could clarify better these 2 fusion algorithms. I have read the article twice and checked some of the references and I’m still a bit confused how each of…

  24. comment
    Comment #37190755

    I feel like something is missing. I see the positive feedback what what about the feedback after rejection?

  25. comment
    Comment #37153795

    The answers so far tend to be either: yes, it’s very easy. Just follow a boot camp or books, transition at work by working close to a DS/ML team, etc., or no, you need lots of back…