Full-text search across 70915 articles. Combine with topic and date filters; results sorted by relevance.
Researchers at an undisclosed institution introduced Reliable Neural Collapse approximation (ReNC), a method for Open-World Test-Time Adaptation (OWTTA) that uses neural collapse as a structural prior to filter out-of-di…
Researchers introduced RecPFN, a prior-fitted network that brings in-context learning to sequential recommendation, achieving state-of-the-art zero-shot performance across eight public benchmarks. RecPFN is pretrained en…
Researchers introduced VGI-bench, a benchmark with 27 tasks and 810 instances for evaluating visual reasoning in video generation models, finding that even the strongest model, Seedance 2.0, achieves only 51.0% accuracy.…
Researchers introduced BERT-LER, a BERT-style model for coded electronic health records (EHRs) that encodes laboratory test results as discrete tokens via percentile-based binning and integrates Integrated Gradients for …
OpenAI's Codex CLI version 0.147.0 lacks explicit cache controls for GPT-5.6 Sol on Amazon Bedrock, causing cache-write tokens to account for about 85% of estimated spend, with 171.94 million cache-write tokens costing a…
Aurey AI's Studio tool focuses on the iterative loop of prompt-to-game creation, allowing users to describe an idea, play a generated version, and refine it through natural language feedback. The tool emphasizes playable…
An independent researcher is seeking a cs.SE endorsement from arXiv to post a paper on mechanically-enforced specification discipline for agentic application rebuilds, which verifies that mechanical hooks change agent be…
OpenRouter has released Ox Alpha, a free stealth reasoning model with a 1 million token context window, designed for coding, agentic work, and production workloads. The model, released on August 20, 2026, is developed by…
A developer released Slack Datamine, an open-source tool that mines Slack's webpack bundle to extract API methods, feature flags, error codes, analytics events, and AI-related enum values, committing each build to a Git …
Base Compute launched Local, a free Mac app that runs AI locally on laptops and workstations, optimizing models for each device's hardware and enabling features like PDF chat, meeting summarization, and coding agents. Th…
Employer health costs are projected to rise 9.5% in 2027 to more than $19,000 per employee, according to benefits consultant Aon, extending a period of near double-digit increases. Workers will pay an average of $5,297 f…
Memorify's MCP gateway delivers a verified 12ms sync for agent tool registration, but multi-tenant memory isolation, vector search latency beyond 100k vectors, and rigid verb protocols limit its use for complex workloads…
A prompt template that assigns a specific persona and constraints turns any large language model into a sharper, more creative writer, according to testing by an unnamed developer. The structure, which pairs a detailed p…
A developer has introduced Concilium, a multi-model method that assigns different roles to AI models such as Claude, Codex, Kimi, and Grok to collaboratively tackle complex problems. The method is designed for scientific…
A developer built Vetta, an AI-powered Shopify audit tool that bluntly critiques stores for conversion issues, using Emergent.sh in a single session. Dissatisfied with the interface and token costs, the developer took th…
A developer reported having 13 open terminals, more than half running Pi or Claude Code, and acknowledged this as a sign of information overload and decision fatigue, linking to resources on cognitive load and a post abo…
Pond, a new open-source tool introduced on Hacker News, lets users archive AI agent sessions into their own S3 bucket or local directory without running a database, using in-process Lance for storage and supporting concu…
Excuse My French, a French-learning exercise generator built on rule-based sentence generation, has been relaunched with an improved UI and new features including flashcards, dictation, and progress tracking. The tool, a…
Apple's upcoming 'HomePad' smart home hub will reportedly feature customizable Apple Watch-style 'faces' and a 'Face Gallery,' according to code discovered by Filipe Espósito at engadget. The HomePad, delayed from an ear…
Binance launched Agent OS, a developer platform connecting AI applications to its trading, market data, wallet, payment, and onchain capabilities, with granular user controls via Agentic sub-accounts that block withdrawa…