1. X
  2. alpha_rover
Log inSign up
alpha_rover
1,465 posts
Image
user avatar
alpha_rover
@Alpha10six
building robots and community with codex - since 2024 codex ambassador - northwest arkansas
USA
Joined January 2025
692
Following
4,027
Followers
RepliesRepliesArticlesArticlesMediaMedia

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
  • Pinned
    user avatar
    alpha_rover
    @Alpha10six
    Jul 13
    The support from @OpenAI & @OpenAIDevs is truly astounding. 😎 Really looking forward to hosting our events during Global Build Week and growing the community! Very humbled to be a part of it. Check out that swag and autograph by @romainhuet 🤯 👀
    Image
    Image
    Image
    8.4K
  • user avatar
    alpha_rover
    @Alpha10six
    13h
    this is a really great area for google/gemini to focus
    user avatar
    Logan Kilpatrick
    Google AI Studio
    @OfficialLoganK
    19h
    Introducing Gemini Robotics ER 2, our latest robotics embodied reasoning model based on Gemini. So much progress from our last ER model (and baseline Gemini 3.6 Flash). Very excited to see more robots do useful things with this model!
    Image
    161
  • user avatar
    alpha_rover
    @Alpha10six
    18h
    sol-none was the winner; consistently beat luna-low, luna-medium, & terra-low in both speed and accuracy. it's now my default for this system. more details on that soon as i'm able to share.
    user avatar
    alpha_rover
    @Alpha10six
    19h
    have spent all morning benchmarking luna, terra, & sol for my system's memory retrieval layer: luna: low reasoning terra: low reasoning sol: none reasoning one of these models was the fastest AND the most accurate. any guesses on which one?
    144
  • user avatar
    alpha_rover
    @Alpha10six
    19h
    have spent all morning benchmarking luna, terra, & sol for my system's memory retrieval layer: luna: low reasoning terra: low reasoning sol: none reasoning one of these models was the fastest AND the most accurate. any guesses on which one?
    370
  • user avatar
    alpha_rover
    @Alpha10six
    Jul 29
    jfc it gets even better 😅
    Image
    Image
    user avatar
    Space Koala
    @SpaceKoala
    Jul 29
    Apparently they're trying to find out exactly where the uncanny valley descends into the canyon of terror.
    780
  • See @Alpha10six's full profile

    Sign up
    Log in
Advertisement
Advertisement