EUNO.NEWS EUNO.NEWS
  • All (16518) +280
  • AI (2550) +21
  • DevOps (732) +17
  • Software (8645) +139
  • IT (4553) +100
  • Education (37) +2
  • Notice
  • All (16518) +280
    • AI (2550) +21
    • DevOps (732) +17
    • Software (8645) +139
    • IT (4553) +100
    • Education (37) +2
  • Notice
  • All (16518) +280
  • AI (2550) +21
  • DevOps (732) +17
  • Software (8645) +139
  • IT (4553) +100
  • Education (37) +2
  • Notice
Sources Tags Search
한국어 English 中文
  • 4 days ago · ai

    Beyond Benchmaxxing: Why the Future of AI Is Inference-Time Search

    Article URL: https://adlrocha.substack.com/p/adlrocha-beyond-benchmaxxing-why Comments URL: https://news.ycombinator.com/item?id=46486290 Points: 3 Comments: 0...

    #inference-time search #AI performance #model benchmarking #LLM optimization #machine learning inference
  • 6 days ago · ai

    REFRAG y la dependencia crítica a los pesos del modelo

    Introducción Llevamos todo el 2025 obsesionados con el tamaño de la ventana de contexto: 128 k, 1 millón, 2 millones de tokens. Los proveedores nos vendían la...

    #LLM optimization #context window #relevance verification #model weight dependency #token efficiency
  • 2 weeks ago · ai

    Two Efficient Technologies to Reduce AI Token Costs: TOON and Microsoft's LLMLingua-2

    'TOON Data Serialization and Microsoft’s LLMLingua‑2 Prompt Compressor

    #token cost #prompt compression #LLMLingua-2 #TOON #LLM optimization #generative AI #cost reduction
EUNO.NEWS
RSS GitHub © 2026