Live data from Hacker News

Viewing profile — tkellogg

tkellogg

HN member
Joined
Tue, Nov 15, 2011, 1:18 AM UTC
HN karma
1,127
Public activity
245 items

About tkellogg

No profile information was provided.

Recent public activity

  1. story
  2. comment
    Comment #45412678

    how is this self promotion? What am I promoting? This post is literally rooted in curiosity, to the core.

  3. comment
    Comment #45412568

    Whelp, it took an hour for this to quickly rise on the front page and then get shadow banned. I guess that says something.

  4. story
  5. story
  6. story
  7. story
  8. story
  9. story
  10. comment
    Comment #44017816

    FYI https://mcp.so/ is the exact same thing as was posted. Not sure why they directed to the github instead of the actual site..

  11. comment
    Comment #43958626

    Somewhere in 2024 I noticed that "AI" shifted to no longer include "machine learning" and is now closer to "GenAI" but still bigger than that. It was never a strict definition, and…

  12. story
  13. story
  14. story
  15. story
  16. story
  17. story
  18. story
  19. comment
    Comment #43007291

    The R1 paper did it as well. Agreed, it's always very interesting.

  20. story
  21. comment
    Comment #42937954

    it's just an example, but it's great to see smolagents in practice. I wonder how well the import whitelist approach works for code interpreter security.

  22. comment
    Comment #42841904

    Additionally, in the following days, I've seen evidence suggesting that the SFT part might not even be necessary. I'd argue that work wouldn't have happened if R1 wasn't released i…

  23. comment
    Comment #42830841

    Ah! My bad, I edited the article to simply quote Francois. Thanks for catching this, Simon.

  24. comment
    Comment #42829777

    Author here. I do believe it's going to be exponential (not yet), but that's out of scope for the article. However, if someone has a good explainer link for that, please put it her…

  25. comment
    Comment #42785100

    I think their thought process is unconvincing, although I think they're probably correct. A much better paper is, "Procedural Knowledge in Pretraining Drives Reasoning in Large Lan…