←Search results

By relevance · Total 3428 results Clear search

Saturday

Friday

  1. LiveKit Product and Engineering Blog

    How LiveKit builds production-grade AI voice agents

    LiveKit has released a guide sharing the experience of its solutions architects and forward-deployed engineers in helping customers move voice agent POCs into production systems, centered on three questions: whether the agent is smart and natural enough, whether production performance can be observed, and whether it can scale reliably and at low cost. The guide offers 7 methods, including measuring first-turn response latency separately, splitting context into the part needed for the greeting and the part loaded in the background, and enabling turn_detection=inference.TurnDetector() and adaptive interruption handling by default.

    Sequence diagram of an agent handling an async claim status lookup: it starts the lookup in the background, keeps talking with the caller, and reports back once the lookup finishes

    LiveKit has released a guide sharing the experience of its solutions architects and forward-deployed engineers in helping customers move voice agent POCs into production systems, centered on three questions: whether the agent is smart and natural enough, whether production performance can be observed, and whether it can scale reliably and at low cost. The guide offers 7 methods, including measuring first-turn response latency separately, splitting context into the part needed for the greeting an

    Matched fieldsBody

  2. The Verge AI

    One week with RTX Spark laptops: How do gaming, local AI, and battery life perform?

    Three authors from The Verge spent a week testing five laptops powered by Nvidia's RTX Spark N1X chip, including the 128GB Surface Laptop Ultra, Asus ProArt P16, Lenovo Yoga 9n, and HP OmniBook Ultra, priced from $3,199.99 to $6,999.99. For gaming, medium settings plus DLSS Performance mode held a steady 60fps in most games, but CPU-bound scenarios such as Helldivers 2 struggled to hit that mark; the authors place its graphics performance roughly between the RTX 5070 and RTX 5060 Laptop GPU. The local AI experience still feels like a developer testing phase: generating a news briefing with Qwen3.8-27B took 10 minutes and consumed 10% of the battery, while battery life for web-based office work came in at around 5 hours.

    Three authors from The Verge spent a week testing five laptops powered by Nvidia's RTX Spark N1X chip, including the 128GB Surface Laptop Ultra, Asus ProArt P16, Lenovo Yoga 9n, and HP OmniBook Ultra, priced from $3,199.99 to $6,999.99. For gaming, medium settings plus DLSS Performance mode held a steady 60fps in most games, but CPU-bound scenarios such as Helldivers 2 struggled to hit that mark; the authors place its graphics performance roughly between the RTX 5070 and RTX 5060 Laptop GPU. The

    Matched fieldsBody