Live data from Hacker News

Viewing profile — ashater

ashater

HN member
Joined
Thu, Sep 22, 2016, 1:39 PM UTC
HN karma
47
Public activity
21 items

About ashater

No profile information was provided.

Recent public activity

  1. comment
    Comment #48830775

    Do you want to monitor what an Al agent is about to do before it acts? In our new paper, Beyond the Black Box: Interpretability of Agentic Al Tool Use, we explore how mechanistic i…

  2. story
  3. comment
    Comment #47603415

    Likely reasoning is part of the original model. It is well known that it is not possible to get a 1bn parameter model to reason, even with RL.

  4. comment
    Comment #44159330

    We want to do both. In finance, highly regulated industry, understanding how models work is critical. In addition, mech interp will allow us to understand which current or new arch…

  5. comment
    Comment #44159259

    Thank you for reading. One of the main reasons we've written the paper is to help with model validation of LLM usage in our highly regulated industry. We are also engaging with reg…

  6. comment
    Comment #44159203

    Our paper provides evidence of features in Finance but I would suggest reading seminal papers from Anthropic https://www.anthropic.com/news/golden-gate-claude and https://transform…

  7. comment
    Comment #44158562

    Thank you. Agreed, we are exploring different ways to apply these interpretability methods to a wide range of transformer based methods, not just decoder based generative applicati…

  8. comment
    Comment #44157619

    Paper introduces AI explainability methods, mechanistic interpretation, and novel Finance-specific use cases. Using Sparse Autoencoders, we zoom into LLM internals and highlight Fi…

  9. story
  10. comment
    Comment #44074598

    Our paper introduces AI explainability methods, mechanistic interpretation, and novel Finance-specific use cases. Using Sparse Autoencoders, we zoom into LLM internals and highligh…

  11. story
  12. comment
    Comment #43380936

    My younger daughter, who is pretty good at making games in Scratch is not that interested in jumping into text/code based programming. I do think Scratch makes things a lot easier …

  13. comment
    Comment #42479059

    Another piece of evidence that LLMs are plateauing

  14. comment
    Comment #41826877

    Terrence Tao has a very healthy view of what AI can and cannot achieve shorter term. It is refreshing to hear more grounded views from a top mathematician who is clearly well verse…

  15. story
  16. story
  17. comment
    Comment #29287814

    Good article, steps one level below container managers like Docker or k8s. Obviously not the indepth of how Linux kernel manages container processes but a good write-up.

  18. comment
    Comment #26265862

    pynq is a good starting board. What's really good is the software environment connected to the fpga logic via Python ecosystem. There are lots of examples via Jupyter notebooks.

  19. comment
    Comment #23155333

    how do I modify the link?

  20. comment
    Comment #23155253

    The paper describes the rise of “tech entrepreneurship as a lifestyle” and how more entrepreneurship seems primarily motivated by people wanting to “be entrepreneurs” rather than b…

  21. story