AINewsnow

Perplexity Releases Decider v1.3 Open-Weight Decision Models with Text-Span Extraction

Perplexity released Decider v1.3 and Decider Flash v1.3 on November 12, 2026, open-weight models returning probabilities rather than text. The update adds verbatim text-span extraction via Locate and reports 91.6% mean accuracy.

Read the full story at Unite.AI ↗

Timeline · 2 reports

  1. 2026-11-13 16:10 · MarkTechPost
    Perplexity Releases Decider v1.3: Open-Weight Decision Models Add Locate
  2. 2026-11-12 18:45 · Unite.AI
    Perplexity Releases Decider V1.3 Models with Text-Span Extraction

More stories

  1. AI chatbots predict how AI companions could reshape relationships by 2030 — Tom's Guide AI
  2. AI reputation management firms gain ground as chatbots shape first impressions — The Next Web
  3. 2026 AI tool roundups compare SEO, social, image, music, comic and security options — DEV Community — AI
  4. Free AI Discoverability Audit by AISONX for AI Search Presence and Performance — DEV Community — AI
  5. Gemini Decision 1 and Decider v1.3: A Decision Layer in Front of Your Agent — DEV Community — AI
  6. The SSAP Protocol: Why We Are Teaching AI to Stop "Talking" and Start "Saving" Travelers in China — DEV Community — AI
  7. How to tell if ChatGPT, Claude or Perplexity send visitors to your site (in any analytics tool) — DEV Community — AI
  8. AI search listed a feature we haven't shipped. Here's how we traced it and the script we now run. — DEV Community — AI

Get the daily brief of stories like this at 6:30 every morning →