Perplexity Decider v1.3: decision models add Locate text-span extraction
Spotted 2026-11-14 15:07 (UTC+8) · original event 2026-11-12 · sources: Hacker News, Perplexity official blog, Unite.AI, AI Primer, ExplainX · spreading on 3 platformsHeat score
Rank score: 6040% — where it sits on the charts
Discussion score: 7040% — how much people are talking about it
Cross-platform score: 7020% — how many platforms it spread to
Composite heat score:46.0rank × 0.4 + discussion × 0.4 + cross-platform × 0.2 — includes a -20-point cooling decay (peak passed, attention fading).
Why it matters
Chat models paraphrase; when you need a yes/no, a score, or the exact span of text, you need a model that decides instead of generating - and open weights for that job were scarce.The angle
Perplexity's new decision model doesn't chat - it judges, scores and pinpoints exact textSuggested format: Short video · for AI followers, developers, LLM app buildersEvidence chain
• HN #16, 120 pts/21 cmt (2026-11-14)• Perplexity official blog 2026-11-12: Decider v1.3 and Decider Flash v1.3 released, new 'locate' feature returns verbatim text spans with character offsets for NER, PII detection and extractive QA, Apache-2.0 weights on Hugging Face, via OpenRouter and Decisions API• vendor-reported 91.6% mean accuracy across 63 query-classification tasks• Unite.AI, AI Primer and ExplainX covered the release• was a 64.0 watch item in rounds 35-41, crossed the line only after this round's search corroboration raised cross-platform score to 70 (Brave/Lilly precedent)• 2026-11-14 16:07 update: HN #17, 122 pts/21 cmt• 2026-11-14 17:07 update: HN #18, 125 pts/22 cmt• 2026-11-14 18:07 update: HN #18, 131 pts/23 cmt• 2026-11-14 19:07 update: HN #17, 131 pts/23 cmt• 2026-11-14 20:07 update: HN #19, 134 pts/23 cmt• 2026-11-14 21:07 update: HN #22, 137 pts/25 cmt• rank 75 -> 60• 2026-11-14 22:08 update: HN #24, 140 pts/25 cmt• 2026-11-14 23:07 update: dropped out of HN top 30• formula 66.0, stored 46.0