Live data from Hacker News

Viewing profile — 0xab

0xab

HN member
Joined
Thu, Feb 26, 2009, 7:52 AM UTC
HN karma
289
Public activity
14 items

About 0xab

[ my public key: https://keybase.io/abarbu; my proof: https://keybase.io/abarbu/sigs/h3mZrqPc43r9yBZzQamt_Z-0RacJ9n2okioUJJpfU6c ] AI researcher at MIT. https://0xab.com

Recent public activity

  1. comment
    Comment #44176315

    > When VLMs make errors, they don't make random mistakes. Instead, 75.70% of all errors are "bias-aligned" - meaning they give the expected answer based on prior knowledge rather t…

  2. comment
    Comment #42504457

    Datasets need to stop shipping with any training sets at all! And they should forbid anyone from using the test set to update the parameters of any model through their license. We …

  3. comment
    Comment #22579787

    I'm the lead author of the paper you cited. Glad you enjoyed our work :) Sure, you can break systems. That doesn't mean that they aren't useful! In many cases a system will see the…

  4. comment
    Comment #20247787

    > merely a student or professor, but can get a job at or create their own a startup or big company or meaningful open source project of their own. Hey! Professors do meaningful thi…

  5. comment
    Comment #20247583

    Years ago we had a lot of good problems. Not just 2006, but 2007 was great too where you had secret messages to save Endo. 2008 at least had you doing some fun things with the rove…

  6. comment
    Comment #20229656

    There's so much wrong with this. HIPAA doesn't talk about US citizens or distinguish different types of records based on any properties of the people that those records cover. The …

  7. comment
    Comment #20195876

    If you use lens as just a way to access records like you do in other languages, then there is absolutely nothing hard about it. Literally all you need to know is: Name your records…

  8. comment
    Comment #19955232

    There's a control group. Both groups were watched by the experimenters. Not only that, the same teachers had students in both groups in different classes.

  9. comment
    Comment #19790510

    This is a huge problem throughout science, not just ML. As scientists, we're rewarded for publishing cool new things that work, not for pointing out things that don't or for pointi…

  10. comment
    Comment #19790326

    I agree, they should do one or the other. The imbalance is totally artificial and objectionable though. Where's the evidence that doctors see a 80/20 split in real life? If there i…

  11. comment
    Comment #19790143

    I do research in computer vision and this paper is so bad it's beyond words. * They give the network is huge advantage: they teach it that it should say "no" 80% of the time. The t…

  12. comment
    Comment #16068053

    That's a common misconception. She did not do jail time for insider trading. She almost certainly would have gotten away with it. The problem is she lied to a federal agent while t…

  13. comment
  14. comment
    Comment #8162420

    In terms of immigrants as a percentage of population the US is nothing special. Canada has a lot more (closer to 19% instead of 14%). Many European countries have statistics simila…