Live data from Hacker News

Viewing profile — mikejulietbravo

mikejulietbravo

HN member
Joined
Fri, Aug 10, 2018, 7:11 PM UTC
HN karma
255
Public activity
133 items

About mikejulietbravo

No profile information was provided.

Recent public activity

  1. comment
    Comment #48645025

    came to say this, there's almost zero history for this so unless their supply chain got meaningfully distorted I can't see why this would happen now

  2. comment
    Comment #48645000

    text editors 5ever

  3. comment
    Comment #48644982

    as benchmarked on AA

  4. story
  5. comment
    Comment #48101838

    The short answer is that it depends how well you define the boundaries of the task and the relative complexity. For example, smaller model is usually fine for something like summar…

  6. comment
    Comment #47537735

    how many mentions of silicon valley?

  7. comment
    Comment #46736178

    seems like more than invested in other inference players

  8. comment
    Comment #45319381

    nuances like idioms can and will be solved. wispr flow is already solving a lot of these things via their speech-to-text interface. as better models are introduced, figurative lang…

  9. comment
    Comment #45319369

    does the plugin architecture come with added overhead (assuming you add a lot of elements)?

  10. comment
    Comment #45319363

    was just glad this wasn't about twitter :)

  11. comment
    Comment #42869310

    Awesome - we'd love to have our CEO/CTO chat with you and your team if you're interested. Shoot me a note at mike.bilodeau @ baseten.co and I'll make it happen!

  12. comment
    Comment #42869108

    Mike from Baseten here We're super proud to support this work. If you're thinking of running deepseek in production, give us a shout!

  13. comment
    Comment #41131654

    The start of this reads like the beginning of a cult manifesto, but then transitions to a very logical solution for an important problem. Baffling. I'm in

  14. comment
    Comment #41131623

    What's the tl;dr on a difference from this to SD?

  15. story
  16. story
    Show HN: 60% higher tokens per second for 70B custom LLMs

    We optimized Writer's Palmyra Fin and Palmyra Med for 60% higher TPS at 35% reduced cost

  17. comment
    Comment #40813349

    This is such a wild undertaking. I love it

  18. comment
    Comment #40813309

    This is the biggest point. You can simply not use them. Cook your own food or walk or drive or bike to a restaurant. There is a massive market of lazy AF people who also are terrib…

  19. comment
    Comment #40813289

    Taxes are not the answer, let the free market figure it out

  20. comment
    Comment #40813264

    I'm kind of surprised they haven't already built this into the LD core

  21. comment
    Comment #40813240

    I remember reading that post, there were a lot of good ideas in the comments

  22. comment
    Comment #40813073

    The new docs are great. Awesome work there

  23. story
    Show HN: Baseten Chains – Framework and SDK for Multi-Model AI Products

    Launched today - happy to answer any and all questions!

  24. comment
    Comment #40212756

    Odd, this looks like it was posted 6 months ago but is back?

  25. comment
    Comment #39716774

    not a criticism here, just a genuine question. What about this makes it friendly for ADHD? Is it a formatting/style thing? Information ordering?