← 트렌딩

Tangerine Index는 ChatGPT 이후 나온 프로덕트와 사람들의 반응을 싣습니다.

Cognition's SWE-2

cognition.com

Cognition's coding model, 64% cheaper than Fable 5.1

cognition.com 방문외부 사이트

제작자가 쓴 설명

Today we’re introducing SWE-2, our most advanced coding model yet. SWE-2 delivers highly competitive agentic coding performance across multiple effort…. SWE-2 is Cognition's new coding model, post-trained from Kimi K3 with RL that optimizes for cost and capability at the same time.

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. Claude Fable 5.1

    Claude’s most advanced models for coding and knowledge work

    anthropic.com최근 반응

    Hacker News
    반응 없음
    Product Hunt
    추천 146
    GitHub
    반응 없음

  2. Edgee Codex Compressor V2

    Use Codex at 35.6% lower costs

    edgee.ai반응 4개최근 반응

    Hacker News
    반응 없음
    Product Hunt
    추천 212
    GitHub
    반응 없음

  3. Komi-learn

    continuous memory and self-improvement for coding agents

    github.com오픈소스반응 2개최근 반응

    Hacker News
    27점
    Product Hunt
    반응 없음
    GitHub
    스타 80

  4. Kimi K2.7 Code

    Kimi’s most capable coding model yet

    huggingface.co최근 반응

    Hacker News
    반응 없음
    Product Hunt
    추천 336
    GitHub
    반응 없음

  5. A plain-text cognitive architecture for Claude Code

    One memory, not one per tool. Cog gives AI agents a shared, structured memory layer using plain-text files — portable across Claude Code, Codex, Cursor, Gemini CLI, Windsurf, Copilot, and more.

    lab.puga.com.br최근 반응

    Hacker News
    157점
    Product Hunt
    반응 없음
    GitHub
    반응 없음