







How we train and evaluate Decider v1.3 and Decider Flash, with locate extraction, real-world results, and costs.
👋 Jan on Twitter / X
Introducing Jan-v1: 4B model for web search, an open-source alternative to Perplexity Pro.In our evals, Jan v1 delivers 91% SimpleQA accuracy, slightly outperforming Perplexity Pro while running fully locally.Use cases:- Web search- Deep ResearchBuilt on the new version… pic.twitter.com/YApIShOAHI— 👋 Jan (@jandotai) August 12, 2025
Perplexity
Perplexity is a free AI-powered answer engine that provides accurate, trusted, and real-time answers to any question.

Perplexity
Perplexity is a free AI-powered answer engine that provides accurate, trusted, and real-time answers to any question.

Decider for Mac - Perplexity
Run pplx-decider-flash-v1.2 on your Mac from the menu bar and call the Decisions API at 127.0.0.1 with no API key.
// Functional Event Sourcing Decider - thinkbeforecoding
Functional Event Sourcing Decider - Jérémie Chassaing

GitHub - AbdelStark/jev-benchmarks at 0d610cc53e79bcbec691312b0c4adb4a0e371642
Probability-aware evaluation for typed decision models: calibration, selective risk, latency, and reproducible benchmarks. - AbdelStark/jev-benchmarks
perplexity-ai/pplx-pii-masking · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Laya — 33ms Multilingual System 1 Decision Engine
Evaluates typed decisions (choice, score, noul) over 100+ languages in a single forward pass with calibrated probabilities. Outperforms TypeSafe Jev.
Perplexity on Twitter / X
New research: Portable Computer is a local-first agent for private and cost-effective work.With an on-device 27B model, our harness scores 82.6% on real knowledge work, beating open-source harnesses Pi and Hermes. Our post-trained PPLX 27B reaches 85.4%. pic.twitter.com/Rb6d47clCI— Perplexity (@perplexity_ai) August 25, 2026

Perplexity on Twitter / X
Introducing Perplexity Computer.Computer unifies every current AI capability into one system.It can research, design, code, deploy, and manage any project end-to-end. pic.twitter.com/dZUybl6VkY— Perplexity (@perplexity_ai) February 25, 2026
Expert Knowledge Elicitation: Subjective but Scientific
Expert opinion and judgment enter into the practice of statistical inference and decision-making in numerous ways. Indeed, there is essentially no aspect of scientific investigation in which judgme...

DeepSeek V4 Flash 0731 scores 50 on the Artificial Analysis Intelligence Index, 10 points above previous DeepSeek V4 Flash
DeepSeek releases DeepSeek V4 Flash 0731

FLF’s Epistemic Case Study Competition: Results — LessWrong
This summer, FLF ran a contest which asked entrants to help us “find the best workflows and methodologies for using AI to produce reliable, trustwort…
Primitive | Decision infrastructure for AI agents
Primitive captures your decisions as you build, shares them with your team, and holds your agents to them.

#Exploration: A Study of Count-Based Exploration for Deep...
Count-based exploration algorithms are known to perform near-optimally when used in conjunction with tabular reinforcement learning (RL) methods for solving small discrete Markov decision...

FLF’s Epistemic Case Study Competition: Results – Future of Life Foundation
This summer, FLF ran a contest which asked entrants to help us “find the best workflows and methodologies for using AI to produce reliable, trustworthy knowledge bases, grounded in real-world cases”.
