Live data from Hacker News

Viewing profile — bigEnotation

bigEnotation

HN member
Joined
Sun, Jul 10, 2022, 3:06 AM UTC
HN karma
24
Public activity
34 items

About bigEnotation

No profile information was provided.

Recent public activity

  1. story
    Show HN: Prompt2pwn – CTF Automated Solver

    Tested it out this [weekend]( https://ctftime.org/team/425785 ), spent $100 across xai ($35), google($35), anthropic($25). - xai:grok-4-1-fast-reasoning solved 8 - google:gemini-3-…

  2. story
    The True State of AI

    Try doing any kind of fantasy sports analysis and you’ll see the fallacy of the current state of LLMs. Pinning y’all’s livelihood to this is wild.

  3. story
  4. comment
    Comment #44217171

    Reasoning models are just wrappers over the base model. It was pretty obvious it wasn’t actually reasoning but rather just refining the results using some kind of reasoning like he…

  5. story
  6. story
    Ask HN: Anyone have old Google Trends Newsletters they could forward me?

    Anyone have old Google Trends Newsletter Emails they could forward me? I'm trying to build a model that embeds the content from the Google Trends Newsletter I've only recently sign…

  7. story
  8. comment
    Comment #40665303

    Link to example workflow: https://github.com/edelauna/stock-predictor/blob/prod/.githu...

  9. story
    GitHub as Storage and Actions as Compute?

    For a personal project I ended up using Github Actions to perform compute functions based on a cron schedule, and then commit the changes back to the repository: https://github.com…

  10. comment
    Comment #40157223

    I wonder what the break even point would be to just have switched to use JVM.

  11. comment
    Comment #40024485

    How could you be a human being and not be small D disgruntled?

  12. comment
    Comment #39965886

    I know it always gets shutdown, but I’m comfortable with it being done by the US/CIA[1], especially since Satoshi stopped sending emails once Gavin Andresen met with CIA and « took…

  13. comment
    Comment #39957904

    Yeah, see GPT 3.5 vs GPT 4 pricing.

  14. comment
    Comment #39957860

    I thought this is what GPT 4 was, it uses a boosting algorithm over GPT 3.5?

  15. comment
    Comment #39887397

    I think you’re forgetting about the use case where the LLM returns something partially correct to a discerning expert, who is still able to use the response, but does not bother wi…

  16. comment
    Comment #38861724

    Does go have something similar to spring, or is there a framework baked into the language

  17. story
  18. comment
    Comment #38790511

    I’ve not had any success to make responses deterministic with these settings. I’m even beginning to suspect historic conversations via API are used to influence future responses, s…

  19. comment
    Comment #38730049

    What’s a quality attribute requirement, and how are they usually documented and prioritized?

  20. comment
  21. comment
    Comment #38692042

    So where is the secret key stored for signing the JWT? In the front end as well? Edit: Oh I found it here: https://postgrest.org/en/stable/how-tos/sql-user-management.... That’s a …

  22. comment
    Comment #38685210

    Truth has always been hard to figure out. An old mentor once told me to be skeptical of everything I hear and only trust half of what I see. When I asked about which half to believ…

  23. comment
    Comment #38654080

    >>> slowest part of software delivery is testing In my experience the slowest part has been marking a feature as done. I loved working at places with QA. I could assign tickets to …

  24. story
  25. comment
    Comment #38347566

    I feel like I’m missing something about this chatGPT craze… to me the product is chatGPT, and it’s mostly fleshed out (would like to see the ability to upload an image, as part of …