24vids light logo
24vids dark logo
24vids mobile logo
  • 首页
  • 热门
  • 趋势
  • 最新
分类
  • 科学技术
  • 游戏
  • 艺术
  • 汽车交通
  • 动物
  • 音乐
  • 旅游
  • 体育
  • 健康养生
  • 新闻政治
  • 教育
  • 喜剧
  • 财经
  • 美食
  • NSFW
热门频道
  • MarioNawfal 的头像
    Mario Nawfal
  • ANI 的头像
    ANI
  • Acyn 的头像
    Acyn
  • centralreality 的头像
    Central Reality
  • Rainmaker1973 的头像
    Massimo
  • SkyNews 的头像
    Sky News
  • atrupar 的头像
    Aaron Rupar
  • whyyoutouzhele 的头像
    李老师不是你老师
  • BGatesIsaPyscho 的头像
    Concerned Citizen
  • AJArabic 的头像
    قناة الجزيرة
  • BFMTV 的头像
    BFM
  • aykiri 的头像
    Aykırı
  • MyLordBebo 的头像
    Lord Bebo
  • siyahsancakx 的头像
    SİYAH SANCAK
  • WWE 的头像
    WWE
  • gorgeous4ew 的头像
    قورجس
  • elchiringuitotv 的头像
    El Chiringuito TV
  • EricLDaugh 的头像
    Eric Daugherty
  • NFL 的头像
    NFL
  • NBA 的头像
    NBA
LIVE
1.2k

Anya Rossi

Live Cam

Watch Now
信息
  • 关于
  • 联系我们

© 2026 24vids.

版权所有。

#alignmentworkshop

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online
Current Status
Live

Private Show

Join now for exclusive access

Free preview available • Premium content

RepE: Representations are weights & activations. Engineering is reading, probing & control—like brain scans for AI. Andy Zou shows how top-down representational engineering improves AI honesty and jailbreak robustness. #AlignmentWorkshop
1:12
farairesearch's profile picture

RepE: Representations are weights & activations. Engineering is reading, probing & control—like brain scans for AI. Andy Zou shows how top-down representational engineering improves AI honesty and jailbreak robustness. #AlignmentWorkshop

FAR.AI

415,329 次观看 • 1 年前

"If you literally catch your AI trying to escape, you have to stop deploying it." Buck Shlegeris shares strategies for managing misaligned AI, including trusted monitoring and collusion-busting techniques to limit catastrophic risks as capabilities grow. #AlignmentWorkshop
0:53
farairesearch's profile picture

"If you literally catch your AI trying to escape, you have to stop deploying it." Buck Shlegeris shares strategies for managing misaligned AI, including trusted monitoring and collusion-busting techniques to limit catastrophic risks as capabilities grow. #AlignmentWorkshop

FAR.AI

194,863 次观看 • 1 年前

Vienna #AlignmentWorkshop: 129 researchers tackled #AISafety from interpretability & robustness to governance. Keynote by Jan Leike + talks by Victoria Krakovna David Krueger Gillian Hadfield Robert Trager Neel Nanda David Bau Helen Toner Mary Phuong and more. Blog recap & videos. 👇
0:34
farairesearch's profile picture

Vienna #AlignmentWorkshop: 129 researchers tackled #AISafety from interpretability & robustness to governance. Keynote by Jan Leike + talks by Victoria Krakovna David Krueger Gillian Hadfield Robert Trager Neel Nanda David Bau Helen Toner Mary Phuong and more. Blog recap & videos. 👇

FAR.AI

46,317 次观看 • 1 年前

没有更多内容可加载