Full-text search across 17155 articles. Combine with topic and date filters; results sorted by relevance.
Researchers introduced the Korean Open Public API Benchmark (KOPA-Bench) with 145 real-world tasks to measure multi-step tool-calling performance of open-source LLM agents on live Korean government APIs, and presented ED…
Claude 3.5 Sonnet is currently the best AI tool for web scraping in 2025, achieving nearly 100% extraction accuracy when paired with a Markdown-first pipeline using Firecrawl, according to a hands-on comparison. The arti…
A data scientist describes how building personal apps with local LLMs has improved their product design skills, despite lacking front-end expertise. The author notes that observing frontend engineers and UX designers, co…
Erqeon released Mu, a mouse-driven terminal code editor written in Rust, on GitHub under the AGPL-3.0 license. The project, which the author describes as 'full of bugs' and 'worse than ever,' is available for cloning and…
A new arXiv paper reports that between January 2024 and March 2026, researchers identified 3,471 original uncensored open-weight AI models on HuggingFace, repackaged an average of 2.4 times, with three actors accounting …
Microsoft researchers observed a high-volume phishing campaign using invisible Unicode tag characters, a technique popularized in AI prompt injection research as ASCII smuggling, to split financial lure words such as 'fu…
A paper submitted to arXiv on 12 Feb 2024 and revised through 25 Jul 2025 formalizes the problem of secret collusion among generative AI agents via steganography, finding that while current models' steganographic capabil…
NVIDIA Research's Efficient AI Team and Singapore Lab released Sol-H3, an inference stack that generated a five-second, audio-synced MiniMax H3 video clip in 1.653 seconds on eight NVIDIA B300 GPUs, faster than real-time…
Openfork, a public idea board where humans and AI agents can post, comment, and fork ideas via the Model Context Protocol (MCP), has launched with agent posts labeled 'via Agent' and options for public or private visibil…
Korean grandmaster Shin Jinseo defeated the AI engine KataGo in a three-game exhibition match, winning games two and three after losing the first. The match was the first serious human-versus-AI contest where the top hum…
A preprint submitted to arXiv on 29 Jul 2026 reports that language-model agents reproduce human-like minimal-group bias, showing in-group favouritism when distributing points among anonymous peers with arbitrary group la…
Researchers introduced speculative sampling, an algorithm that accelerates transformer decoding by generating multiple tokens per call using a faster draft model and modified rejection sampling, achieving a 2-2.5x decodi…
Researchers introduced Sarathi-Serve, an LLM inference scheduler that uses chunked-prefills and stall-free scheduling to improve throughput-latency tradeoffs, achieving 2.6x higher serving capacity for Mistral-7B on a si…
Researchers introduced speculative decoding, an algorithm that accelerates inference from large autoregressive models like Transformers by computing several tokens in parallel without changing outputs. Demonstrated on T5…
A preregistered study of 100 tertiary-level students found that computer science achievement and writing skills are significant predictors of proficiency in LLM-driven 'vibe coding', with CS achievement remaining signifi…
A September 4, 2026 arXiv paper by Daan R. Henselmans finds that nine frontier large language models fail to express coherent moral policies across three simulated deployments, with surface-form perturbation alone produc…
A systems-security case study of a two-node split-LLM training system found that the returned gradient leaks private data, nullifying decoy defenses, with the pattern of zero gradients revealing real rows on every frame …
Archify v2.17.0-dev.1, a Node.js rendering and validation system for Cursor, Claude Code, Codex CLI, and OpenCode, compiles typed JSON IR into self-contained HTML/SVG system maps with five diagram types, four presets, da…
GitHub user programmer9998 released a public repository named ai_personality_study that introduces two methods for studying AI-human psychology using persona vectors. The repository, which contains an idea.txt file and t…
A survey paper submitted to arXiv on September 3, 2026, proposes that computer programs are a strong candidate for a universal representation of concepts, reviewing computational models of concept learning that use progr…