Live data from Hacker News

Viewing profile — jaehong747

jaehong747

HN member
Joined
Mon, Jun 07, 2021, 5:39 AM UTC
HN karma
16
Public activity
28 items

About jaehong747

No profile information was provided.

Recent public activity

  1. comment
    Comment #48812631

    [flagged]

  2. comment
    Comment #48812512

    Good interpretability work, but the problem is it's all in how you interpret it. Bridge concept neurons activating even while talking about something else, this seems pretty obviou…

  3. story
  4. story
    Show HN: Claude Code Spinner Verbs Extractor

    extract & customize ~/.claude/settings.json { "spinnerVerbs": { "mode": "replace", "verbs": [ " Thundering 천둥치는중", " Clauding 클로딩하는중", " Cooking 요리하는중" ] } }

  5. story
  6. comment
    Comment #46729740

    In the AI Era, Do Startups Still Have an Edge? Startups have always competed with big companies based on three gaps: speed, risk tolerance, and incentives. The question is whether …

  7. comment
    Comment #44400917

    great job! it reminds me genaiscript. https://microsoft.github.io/genaiscript/ // read files const file = await workspace.readText("data.txt"); // include the file content in the p…

  8. comment
    Comment #44085760

    Graham says good writing sounds good and is more likely to be true. But his own writing is hard to read and confusing. His sentences are long and messy. If he’s right, then his own…

  9. comment
    Comment #43520820

    Like you, I also find the paper's findings interesting. I'm not arguing that LLMs lack the ability to "think" (mechanically), but rather expressing concern that by choosing the wor…

  10. comment
    Comment #43520749

    Modern transformer-based language models fundamentally lack structures and functions for "thinking ahead." And I don't believe that LLMs have emergently developed human-like thinki…

  11. comment
    Comment #43505242

    I’m skeptical of the claim that Claude “plans” its rhymes. The original example—“He saw a carrot and had to grab it, / His hunger was like a starving rabbit”—is explained as if Cla…

  12. comment
    Comment #43484023

    Wow, quickly skimmed the paper, this really is like a USB stick for knowledge. Thanks for sharing! Cool that you worked on something similar before.

  13. comment
    Comment #43483493

    Yeah, it's definitely attracting attention! Have you tried it yet?

  14. story
    Ask HN: Will Anthropic's MCP succeed as an AI integration standard?

    Anthropic introduced MCP (Model Context Protocol) on November 26, 2024, aiming to standardize how advanced AI models integrate with external data sources. Initially, MCP didn't att…

  15. comment
    Comment #41106605

    FastHTML is an impressive and innovative idea. It seems like a web development tool similar to Streamlit, but with more precise control. FastHTML's concept led me to consider a fea…

  16. comment
    Comment #41091553

    At the Bitcoin Conference 2024, presidential candidate Trump's speech increased the possibility of strategic Bitcoin holdings for the United States. Senator Cynthia Lummis also int…

  17. story
  18. comment
  19. comment
    Comment #41084688

    Thank you. I didn't know that.

  20. comment
    Comment #41084683

    I wanted to argue that Llama 3.1 is not truly open source, and I wanted to discuss this with the public. Looking at previous "Ask HN" posts, it appeared to be a board where both qu…

  21. comment
    Comment #41084659

    Thank you.

  22. comment
    Comment #41083911

    Is the Llama 3.1 model open source? Yes. Really? No. Training Data = Source Code This time, the Llama 3.1 model was released as open source. However, the training data is not discl…

  23. story
  24. story
  25. story