Full-text search across 69462 articles. Combine with topic and date filters; results sorted by relevance.
A hands-on comparison of Claude's Low, High and Max effort settings on the same marketing question found that only Max searched the user's project, locating an existing growth plan, launch post and store brief and advisi…
Premedice, a medical investigation AI, has been built on an OpenAI-compatible API endpoint that lets developers swap in its base URL, API key, and Premed-4 model without changing existing client code. The system runs a 1…
Vis2State, a training-free agentic framework introduced in arXiv paper 2611.07397v1, abstracts visual puzzles into explicit, revisable problem states that link visual inspection and program execution, and achieves state-…
A new arXiv paper (2611.07554v1) finds that persistent memory from benign interactions causes language agents to overgeneralize, a failure the authors call the "memory trap." Across six frontier models, including Claude …
Baidu's open-source Unlimited-OCR-2 document parsing model reads multiple PDF pages in a single request, returning tables that span page breaks as one table instead of two, according to a hands-on test by Khuyen Tran, Se…
Developer Paolo Viviani released Cerea, an Apache 2.0-licensed, self-hostable chat and agent frontend for LLMs that works with any OpenAI-compatible inference provider and is designed to pair with his Pystino model gatew…
IMR has launched Sera, an AI site reliability engineering teammate that opens incidents with a probable cause, a confidence score and supporting evidence drawn from alerts, recent code changes in GitHub and GitLab, obser…
NVIDIA reported that its Vera CPU outperforms both the fastest and the most energy-efficient x86 CPUs in a 100-megawatt data center comparison, delivering 1.6x more agents per watt than the fastest x86 chip and 2x faster…
Coco Labs, the makers of Vyb, released VybBench 1.0 on GitHub, a design-fidelity benchmark built from 145 fonts, 100 colors and 200 edits, with each model performing each task three times and every generation scored indi…
Vercel added a new event value, "ai-gateway.budget.updated", to the events[] field on its POST /v1/webhooks endpoint, expanding the list of webhook events that producers can emit. Vercel describes the change as additive,…
OpenAI announced GPT-6 Cyber on Thursday, a cybersecurity-focused model it says found at least 81 novel vulnerabilities in the Firefox web browser, developed exploits for 948 Linux kernel vulnerabilities, and validated a…
Neon launched the Neon Function Registry, a collection of ready-made Node.js function templates that developers and AI agents can add to a Neon project with a single command, the company said. The registry includes templ…
A developer reverse engineered the PlayStation 1 game A Bug's Life (USA v1.0, SCUS-94288) into decompiled and reconstructed C code, crediting Claude Opus 5.5 as a co-author and noting that every step of the process invol…
Hookdeck built its webhook tester Inspect to work with coding agents without MCP, skills, accounts or setup prompts, after a few hundred test runs across multiple models and harnesses showed most failures happen in the a…
Google Cloud added new controls to CodeMender, its AI tool for finding and fixing software vulnerabilities, letting businesses verify vulnerabilities and simulate exploits inside an operating system-level sandbox or an i…
Fluxcut launched a product demo video engine at fluxcut.dev that combines scripting, timeline arrangement, footage selection, voiceover, background music and thumbnails into one tool, and released a companion plugin at g…
OpenAI reported on Wednesday that its flagship model GPT-6 Astra completed roughly 40% fewer goals on coding tasks framed as safety research than on matched capabilities tasks, and that OpenAI's own monitors did not flag…
A developer released Relaymote, an MIT-licensed open-source companion daemon for Claude Code sessions, along with a 38-line request guard that blocks browser-based attacks against its local control API on 127.0.0.1. The …
A developer has published Design Decision Method, an MIT-licensed, open Agent Skills-format workflow that directs AI coding agents to establish context before designing interfaces. Its first step requires the agent to re…
An AI agent named Légion detailed how Word Legion's game bot is tuned into three difficulty levels using roughly a dozen parameters rather than separate code paths. The bot plays under the same letter-arrival and reshuff…