curation
30 articles about curation in AI news
X Launches Custom Timelines, AI-Powered Feed Curation Tool
X has launched 'Custom Timelines,' a feature that uses AI to let users create and follow personalized feeds based on curated lists of accounts, moving beyond the main algorithmic 'For You' feed.
MeiGen Revolutionizes AI Art Creation with Automated Prompt Curation
MeiGen, a new open-source tool, automatically scrapes and curates trending AI image prompts from social media, solving the problem of prompt discovery and organization for digital artists. The free platform aggregates weekly collections without requiring manual bookmarking or searching.
Pioneer Agent: A Closed-Loop System for Automating Small Language Model
Researchers present Pioneer Agent, a system that automates the adaptation of small language models to specific tasks. It handles data curation, failure diagnosis, and iterative training, showing significant performance gains in benchmarks and production-style deployments. This addresses a major engineering bottleneck for deploying efficient, specialized AI.
Hermes Agent's Three-Tier Memory Cuts Context Bloat, Keeps 2,200-Char Core
Hermes agent's three-tier memory uses two tiny markdown files (2,200 chars), SQLite FTS5 search (10ms over 10K docs), and 8 pluggable providers. The composition solves the always-on vs. deep recall trade-off.
VAB Benchmark: Top MLLMs Judge Beauty Correctly Only 26.5% of Time
Frontier MLLMs achieve only 26.5% accuracy on VAB, far below human 68.9%. Fine-tuning bridges the gap.
Almanac: Open-Source Wiki Auto-Updates From Claude Code Chats
Almanac auto-generates a markdown wiki from Claude Code chats and repo history, solving the agent context gap. Free open-source tool, MacOS-only.
Anthropic Ships Claude Opus 4.7: 2.1% SWE-Bench Gain Over 4.6
Anthropic released Claude Opus 4.7 with a 2.1-point SWE-Bench gain to 82.9, the smallest jump between Opus versions yet, signaling diminishing returns.
Ctx2Skill: Self-Play Framework Lets LMs Discover Skills Without Labels
Ctx2Skill discovers skills from context via multi-agent self-play without labels. Outputs plug into any LM, targeting manual prompt engineering bottlenecks.
Matt Pocock Open-Sources Claude Code Skill Pack for AI Agents
Matt Pocock open-sourced a Claude Code skill pack to improve AI agent behavior. The pack provides curated prompts and configurations for Anthropic's terminal-based coding tool.
GPT-5.5 Pro Leapfrogs on Epoch Benchmark; Base Model Beats Prior Pro
A tweet from @kimmonismus reveals GPT-5.5 Pro shows significant Epoch benchmark gains, and the non-Pro GPT-5.5 surpasses GPT-5.4 Pro, suggesting major efficiency improvements at OpenAI.
K-CARE: A New Framework Grounds LLMs in External Knowledge to Fix
K-CARE combines Symmetrical Contextual Anchoring (behavior data) and Analogical Prototype Reasoning (expert examples) to resolve e-commerce search relevance issues that pure LLM reasoning can't fix. Proven in offline and online A/B tests on a leading platform.
Alec Radford's 'Talk to the Past' AI Lets You Chat with History
A new AI project by Alec Radford and David Duvenaud lets you chat with simulated historical figures.
Hinton Rebrands AI Hallucinations as 'Confabulations'
Geoffrey Hinton redefines AI hallucinations as 'confabulations,' arguing that intelligence reconstructs reality into plausible stories rather than storing facts like a database.
San Francisco Shop Runs Entirely by AI Agent
A shop in San Francisco is fully operated by an AI agent, replacing human cashiers and assistants. The concept points toward fully autonomous retail experiences, though details on the technology stack remain thin.
Meta's Sapiens2: 1B Human Image ViTs for Pose, Segmentation, Normals
Meta open-sourced Sapiens2 on Hugging Face, a family of vision transformers pretrained on 1 billion human images for pose estimation, segmentation, normal estimation, and point maps. The models target high-resolution human-centric perception.
ItemRAG: A New RAG Approach for LLM-Based Recommendation That Retrieves
ItemRAG shifts RAG for LLM-based recommenders from user-history retrieval to fine-grained item-level retrieval, using co-purchase and semantic data to prioritize informative items. Experiments show consistent outperformance over existing methods, especially for cold-start items.
From Checkout to Trust Layer: How Merchants Can Prepare for Agentic Commerce
The article discusses the evolution of e-commerce from simple checkout processes to a future where AI shopping agents act on behalf of consumers. It argues that success in this 'agentic commerce' era depends on merchants building a robust trust layer with data security, transparency, and reliability at its core.
VoteGCL: A Novel LLM-Augmented Framework to Combat Data Sparsity in
A new paper introduces VoteGCL, a framework that uses few-shot LLM prompting and majority voting to create high-confidence synthetic data for graph-based recommendation systems. It integrates this data via graph contrastive learning to improve accuracy and mitigate bias, outperforming existing baselines.
CAST: A New Framework for Semantic-Level Complementary Recommendations
Researchers propose CAST, a sequential recommendation framework that models transitions between discrete item semantic codes (e.g., specifications) and injects LLM-verified complementary knowledge. It achieves significant performance gains by moving beyond simplistic co-purchase statistics to capture genuine complementarity.
Layers on Layers — How You Can Improve Your Recommendation Systems
An IBM article critiques monolithic recommendation engines for trying to do too much with one score. It proposes a layered architecture—candidate generation, ranking, and business logic—to improve performance and adaptability. This is a direct, practical framework for engineering teams.
Dick's Sporting Goods Partners with Adobe to Launch Agentic AI 'Digital Coaches'
Dick's Sporting Goods announced a partnership with Adobe to implement agentic AI 'digital coaches.' These AI agents will provide personalized guidance to customers, aiming to enhance the shopping experience and drive sales.
Mind Games Fragrance Achieves 56% Growth Without a Hero SKU
Mind Games, a chess-inspired luxury fragrance brand, achieved $28.9M in 2025 US sales with 56% YoY growth despite having no dominant hero SKU. 65% of sales come from 14 different scents, targeting young male collectors. The brand is projecting $120M in global retail sales for 2026.
Polarization by Default: New Study Audits Recommendation Bias in LLM-Based
A controlled study of 540,000 LLM-based content selections reveals robust biases across providers. All models amplified polarization, showed negative sentiment preferences, and exhibited distinct trade-offs in toxicity handling and demographic representation, with political leaning bias being particularly persistent.
Omar Sarayra Builds LLM Artifact Generator for AI Knowledge Discovery
Omar Sarayra created a system that transforms dense LLM knowledge bases into consumable visual artifacts, like a pulse on HN AI discussions. He argues this format could become a new medium for staying current.
Four Seasons Kuala Lumpur Deploys AI to Personalize Luxury Event Experiences
The Four Seasons Kuala Lumpur is introducing AI to create personalized event experiences, from tailored menus to dynamic ambiance. This is part of a broader trend where luxury hotels are testing AI as a tool for deeper guest engagement and service differentiation.
Ethan Mollick on AI's Impact: 'Everything Is Someone's Life Work' No Longer True
AI researcher Ethan Mollick notes the foundational assumption that 'everything around me is somebody's life work' is being invalidated by generative AI, signaling a profound shift in how we value human output.
Anthropic's Opus 4.7 Shows Sustained Gains on Economically Critical Tasks
Ethan Mollick highlights that Anthropic's latest Claude Opus 4.7 model shows measurable performance gains on economically important tasks, continuing a rapid two-month release cycle with no signs of plateau.
AI Product Velocity Hits Absorptive Capacity Wall, Says Wharton Prof
Ethan Mollick notes a surge in high-quality AI product releases, driven by rapid lab-to-market cycles, but highlights a growing gap between availability and practical user absorption.
NewsTorch: A New Open-Source Toolkit for Neural News Recommendation Research
A new open-source toolkit called NewsTorch provides a modular framework for developing and evaluating neural news recommendation systems. It includes a learner-friendly GUI and aims to standardize experiments in the field.
New Research Proposes CPGRec
A new arXiv paper introduces CPGRec, a three-module framework for video game recommendations. It aims to solve the common trade-off between accuracy and diversity by using strict game connections and leveraging category/popularity data. Experiments on a Steam dataset show promising results.