Live data from Hacker News

Viewing profile — GL26

GL26

HN member
Joined
Sat, Mar 21, 2026, 5:07 PM UTC
HN karma
237
Public activity
102 items

About GL26

https://gauthier-lechevalier.com/

Recent public activity

  1. story
  2. story
  3. story
  4. story
  5. story
  6. comment
    Comment #48757907

    Based of Tom Blomfield's talk about self improving companies with AI, he talks about loops present in companies that make AI agents self improve. He talks about loops that look lik…

  7. story
  8. comment
    Comment #48745814

    Get ready for the great revolt

  9. comment
    Comment #48743350

    The POC was made to classify materials, we couldn't get our hands on scientific grade materials that would allow to test our hypothesis, so we falled back to just identifying mater…

  10. comment
    Comment #48743337

    Yes, it is half baked, we stopped because the quantity of data needed to continue was too expensive. Concerning the materials that were in the confusion matrix that you saw, it was…

  11. comment
    Comment #48743287

    Your comment still has a lot of value, I didn't detail it in the article but this radar is usually used for autonomous vehicles, or person tracking.

  12. comment
    Comment #48743260

    Hi, thank you so much for your comment, the research was cool to do, but the market isn't there, and this is not something people really want (to retake YC's wording). You can have…

  13. comment
    Comment #48738871

    small note : the website wasn't coded to handle such a trafic, I had to inject a few netlify credits to keep the website alive. The videos are now linked on youtube (they are initi…

  14. comment
    Comment #48738512

    you could definetly equip you wall-e with this sensor, but honestly a camera with yoloV26 + fine tuning for trash recognition would be enough

  15. comment
    Comment #48738488

    exact, if I was carrying a PhD (which I am not). I think I would have wanted to go out further and get more data to make this device pass regulatory tests. What was the status quo …

  16. comment
    Comment #48738386

    overtech for a problem that had a solution (asbestos sensing is pretty painful in Europe), but anyways the market was shrinking, and the TAM was totally not VC backable. Tested it …

  17. comment
    Comment #48738344

    the FMCW tech makes it impossible to have a resolution inferior to 2.5 cm, (so if two layers are appart, you can't physically tell them appart using physical classical modeling tec…

  18. comment
    Comment #48738098

    hahaha ! oops didn't mute the video, would blast trap music when I was alone in the lab x)

  19. comment
    Comment #48737761

    thanks :) !!

  20. comment
    Comment #48737755

    thank you so much for your feedback, it was hard to admit defeat, but at the end looking back at what I built, the parts where I learnt about RF, and just struggled, refactoring th…

  21. comment
    Comment #48737722

    just fixed it, hope it works

  22. comment
    Comment #48737670

    My netlify crashed fixing the website rn

  23. comment
    Comment #48736886

    How many tx and rx antennas did you have ? (I don’t know if it was clear, my stack was 57-64 GHz, 2TX , 3RX)

  24. story
  25. comment
    Comment #48686813

    Feels like identity control is not such a bad thing (prevents bots, identity thefts, cyberbullying, ect...). The questions is not "if it happens", its more a "who controls it?". If…