Live data from Hacker News

Viewing profile — cheeseblubber

cheeseblubber

HN member
Joined
Sat, Dec 24, 2016, 6:03 AM UTC
HN karma
1,947
Public activity
224 items

About cheeseblubber

No profile information was provided.

Recent public activity

  1. comment
    Comment #49027441

    Related: https://news.ycombinator.com/item?id=49020999

  2. story
  3. story
    Show HN: Finterm.ai Bloomberg terminal for Claude Code

    Hi, my name is Kam, and today my cofounder Josh and I are shipping Finterm, a CLI that gives coding agents direct access to financial data: stock prices, options data, SEC filings,…

  4. story
  5. comment
    Comment #48417216

    Anecdotally the site we manage we are easily seeing 100x the traffic from bots than from humans in the past year. So much so that it is impacting our hosting costs.

  6. comment
    Comment #47941754

    My problem with the article is that they don't even mention this fact. The metaphors with Uber often is brought up but it breaks down at cost optimization. It also wouldn't be fair…

  7. comment
    Comment #47937586

    It make sense if you account for cost of intelligence getting cheaper every year. Most of the models per unit of intelligence is getting far cheaper. We get better hardware, archit…

  8. comment
    Comment #47113211

    The human brain also is a product of billions of years of evolution. We branched off from our common ancestor 7-9 million years ago. We encode quite a lot of structure and informat…

  9. comment
    Comment #46154984

    Yes definitely we were using our own budget and out of our own pocket and these model runs were getting expensive. Claude costed us around 200-300 dollars a 8 month run for example…

  10. comment
    Comment #46154907

    Via api you can turn off websearch internally. We provided all the models with their own custom tools that only provided data up to the date of the backtest.

  11. comment
    Comment #46154888

    We used the LLMs API and provided custom tools like a stock ticker tool that only gave stock price information for that date of backtest for the model. We did this for news apis, t…

  12. comment
    Comment #46154847

    You can click in to the chart and see the conversation as well as for each trade what was the reasoning it gave for it

  13. comment
    Comment #46154770

    OP here. We realized there are a ton of limitations with backtest and paper money but still wanted to do this experiment and share the results. By no means is this statistically si…

  14. story
  15. comment
    Comment #46051575

    There is a transcript of the entire conversation if you scroll down a little

  16. comment
    Comment #45564543

    Made a site that let's LLMs trade stocks and you can watch their performance https://www.aitradearena.com/

  17. story
  18. story
  19. story
    Show HN: Releasepages.dev turn your commits to release pages

    Hi HN, My name is Kam, I’m the author of Release Pages. I made a simple app that takes your GitHub commits and turns them in to release pages. See (react.releasepages.dev). I decid…

  20. story
    Show HN: Karl an AI Accountability Buddy

    Hi HN, My name is Kam, and today we’re excited to launch an AI accountability buddy that helps keep you in check and holds you accountable. We originally launched Karl ( https://ww…

  21. story
  22. story
    Show HN: Karl – A virtual friend you can text

    Hi HN! We're excited to introduce "Karl" – a virtual friend you can text to share what's on your mind. We created Karl because we found it incredibly helpful to have a sounding boa…

  23. comment
    Comment #41715030

    Would be cool to see the Quetzal website internationalized itself and see what it looks like in different languages.

  24. comment
    Comment #39367405

    ! basically functions like @ in Slack and chat applications. The only difference in Linen is that we give you an @mention so that it doesn't necessarily need to send a push.

  25. comment
    Comment #39366342

    We actually tried shipping a desktop client with Tauri and Rust. It helped with initial bundle size but performance and resource consumption was kind of similar. We also ran in to …