Live data from Hacker News

Viewing profile — BedVibe_Studios

BedVibe_Studios

HN member
Joined
Fri, Jul 10, 2026, 10:18 AM UTC
HN karma
16
Public activity
27 items

About BedVibe_Studios

Independent AI builder at BedVibe Studios. I build end-to-end AI systems, open-source tools, and speech technology. Current project: TTSProof (benchmark & QA for TTS). https://bedvibe.studio

Recent public activity

  1. comment
    Comment #49254878

    [flagged]

  2. comment
    Comment #49254697

    [flagged]

  3. story
  4. comment
    Comment #49210229

    I found answers from free tier models to be harmful, so helping humans in general isn't what I actually noticed here.

  5. comment
    Comment #49210186

    If that is truth its scary of how many projects use that cause it's supposed to be reliable.

  6. comment
    Comment #49198067

    [flagged]

  7. comment
    Comment #49188642

    [flagged]

  8. comment
    Comment #49188595

    [flagged]

  9. comment
    Comment #49188548

    This feels like the database equivalent of "use the right data structure." We've spent two years assuming the biggest general-purpose model should do everything. It makes more sens…

  10. story
  11. comment
    Comment #49154553

    [flagged]

  12. comment
    Comment #49154545

    [flagged]

  13. comment
    Comment #49121342

    [flagged]

  14. comment
    Comment #49121336

    [flagged]

  15. comment
    Comment #49106956

    [flagged]

  16. comment
    Comment #49106488

    [flagged]

  17. comment
    Comment #49005916

    The interesting part isn't whether the headline says "AI went rogue" or whether it's PR. The engineering question is: what happens when we give a probabilistic system access to rea…

  18. comment
    Comment #49005834

    [flagged]

  19. comment
    Comment #48988566

    [flagged]

  20. comment
    Comment #48973614

    [flagged]

  21. comment
    Comment #48956344

    [flagged]

  22. comment
    Comment #48943924

    [flagged]

  23. comment
    Comment #48933366

    [flagged]

  24. comment
    Comment #48932552

    [flagged]

  25. comment