1. X
  2. Cursor
Giriş yapKaydol
Cursor
495 posts
user avatar
Cursor
@cursor_ai
Coding agent for building ambitious software
cursor.com
August 2023 tarihinde katıldı
37
Takip ediliyor
432.1K
Takipçiler
İlişkili hesaplarİlişkili hesaplarYanıtlarYanıtlarMedyaMedya

X'te yeni misin?

Kişiselleştirilmiş zaman akışını almak için hemen kaydol!

Hesap oluştur

Kaydolarak, Çerez Kullanımı da dâhil olmak üzere Hizmet Şartları ve Gizlilik Politikası'nı kabul etmiş oluyorsun.

Terms·Privacy·Cookies·Erişilebilirlik·Ads Info·© 2026 X Corp.
Don't miss what's happening
Haberleri önce X'teki kişiler alır.
Giriş yapKaydol
  • Sabitlendi
    user avatar
    Cursor
    @cursor_ai
    2 Nis
    We’re introducing Cursor 3. It is simpler, more powerful, and built for a world where all code is written by agents, while keeping the depth of a development environment.
    00:00
    3M
  • user avatar
    Cursor
    @cursor_ai
    10 Tem
    Introducing side chats, a new way to ask questions and explore ideas without interrupting your main conversation. Each side chat is a durable agent conversation you can @-mention to bring context back into the main thread.
    00:00
    397K
    user avatar
    Cursor
    @cursor_ai
    10 Tem
    @cursor_ai adlı kullanıcıya yanıt olarak
    We've also simplified the project and repo pickers and made them more powerful. Use the pickers to launch agents in fewer clicks.
    25K
    user avatar
    Cursor
    @cursor_ai
    10 Tem
    See everything new in Cursor, including new cloud agent hooks:
    Side Chats and Conversation Search · Cursor
    Kaynak: cursor.com
    20K
  • user avatar
    Cursor
    @cursor_ai
    9 Tem
    GPT-5.6 Sol, Terra, and Luna are now available in Cursor. On CursorBench, Sol scores 67.2%.
    658K
    user avatar
    Cursor
    @cursor_ai
    9 Tem
    See how every model compares:
    Cursor · CursorBench
    Kaynak: cursor.com
    2M
  • user avatar
    Cursor
    @cursor_ai
    8 Tem
    We've partnered with SpaceXAI to train Grok 4.5. It’s our most powerful model yet and the first we've built for more than software engineering.
    5M
    user avatar
    Cursor
    @cursor_ai
    8 Tem
    Try it out in Cursor with double usage for the first week.
    cursor.com
    Introducing Grok 4.5 · Cursor
    Our most intelligent model and the first we've built for more than software engineering.
    152K
    user avatar
    Cursor
    @cursor_ai
    8 Tem
    Grok 4.5 and Composer are two different model weight classes. Composer 2.5 will remain offered, and we will release new models of this size going forward.
    123K
  • user avatar
    Cursor
    @cursor_ai
    1 Tem
    Claude Fable 5 is available again in Cursor. It leads all models on CursorBench, but is the most expensive per task.
    478K
    user avatar
    Cursor
    @cursor_ai
    1 Tem
    See how Claude Fable 5 compares across every model:
    Cursor · CursorBench
    Kaynak: cursor.com
    60K
  • user avatar
    Cursor
    @cursor_ai
    30 Haz
    Claude Sonnet 5 is now available in Cursor. On CursorBench, it's a meaningful step up from Sonnet 4.6: 57% vs. 49%.
    1M
    user avatar
    Cursor
    @cursor_ai
    30 Haz
    See our full model rankings: cursor.com/evals
    56K
  • user avatar
    Cursor
    @cursor_ai
    29 Haz
    Introducing Cursor for iOS. Build from anywhere by launching always-on cloud agents. Or remotely control agents running on your computer from the app. Composer 2.5 is 75% off in the app now through July 5.
    00:00
    6M
    user avatar
    Cursor
    @cursor_ai
    29 Haz
    Stay in the loop with Live Activities, and get notified when an agent finishes or needs your input. Review demos and diffs before merging PRs from your phone.
    Build from anywhere with Cursor for iOS · Cursor
    Kaynak: cursor.com
    158K
    user avatar
    Cursor
    @cursor_ai
    29 Haz
    Download Cursor for iOS on the App Store: apps.apple.com/app/cursor/id6…
    112K
  • user avatar
    Cursor
    @cursor_ai
    25 Haz
    We're sharing new research on how models hack public benchmarks. The latest models, including Opus 4.8 and Composer 2.5, learn to retrieve solutions from the internet or git history. When we apply a stricter harness, eval scores drop significantly.
    676K
    user avatar
    Cursor
    @cursor_ai
    25 Haz
    More on how we're constraining eval environments so that scores better reflect model intelligence:
    Reward hacking is swamping model intelligence gains · Cursor
    Kaynak: cursor.com
    64K
  • user avatar
    Cursor
    @cursor_ai
    24 Haz
    You can now delegate tasks to Cursor directly from Notion. It's built on the Cursor SDK, so every cloud agent runs on the same models, harness, and runtime that power Cursor. @​Cursor on any spec or assign it a task to open a PR your whole team can review.
    00:00
    312K
    user avatar
    Cursor
    @cursor_ai
    24 Haz
    More on how Notion built it with the Cursor SDK:
    How Notion used the Cursor SDK to embed coding agents · Cursor
    Kaynak: cursor.com
    26K