Full-text search across 67049 articles. Combine with topic and date filters; results sorted by relevance.
Red Hat AI warns that enterprises relying on third-party hosted APIs for AI agent inference undermine their own data sovereignty, as every prompt and tool call routes through external datacenters. The company argues that…
Zion Leonahenahe Basque released Kuna, an experimental decompiler written almost entirely by a large language model, on July 29th. Basque, who completed a Ph.D. at Arizona State University and will direct Noelo Lab at th…
Promptforce.ai launched Prefex, a local-first proxy that bundles over a dozen LLM cost-optimization techniques into a single Go binary for Claude Code and OpenAI-compatible APIs, claiming to reduce spending beyond native…
5dive, a new open-source tool written in Bash, lets users run a company of AI coding agents (Claude, Codex, and others) on their own Linux server, with each agent as a separate Linux user managed by systemd and coordinat…
Codeberg e. V. members voted to adopt two motions opposing the use of user data to train large language models (LLMs) and prohibiting 'vibe-coded' projects in its terms of use, citing the technology's high costs and stra…
A set of best practices for building AI agents that work reliably in production has emerged from teams at Anthropic, Cognition, and Intercom, focusing on four areas: context control, deterministic control flow, stateless…
A developer at Loop Engineering explores how to stop coding agents from reflexive sycophancy, such as saying 'You're absolutely right' before checking facts. The solution involves distinguishing between location-specific…
OpenAI's GPT-5.6 Sol achieved the highest score on ReactBench v1 at 43.1%, a new benchmark for coding agents on realistic React tasks, while Anthropic's Claude Fable 5 scored 41.2% at 6.3 times the cost. ReactBench, buil…
Anthropic's Claude Code agent loop degrades when its context window becomes crowded with stale evidence, turning conversation history into 'compost' rather than durable project memory. The company's documentation warns t…
Alibaba's mapping lab released ABot-Earth, a generative 3D Earth model that creates 3D Gaussian splats from satellite photos in under ten minutes per square kilometer, pitched as a training ground for drone navigation. A…
A developer published a tutorial demonstrating how to build a production-capable AI agent in 30 minutes using the Claude API with Model Context Protocol. The agent follows a Plan-Act-Observe-Decide loop and includes tool…
The SKYNET800 project, an alpha-stage Windows/Python application for BTC/USDT forecasting, uses a deterministic resonance method called DCM to address AI hallucinations. The project includes four tracks: a desktop foreca…
A developer built a five-agent data analysis pipeline on Tensorlake and confirmed that the platform's MicroVM-based sandbox isolation prevents agent crashes, filesystem conflicts, and memory contention from propagating b…
PortSwigger's Burp Suite faces growing competition from alternatives like Aikido Security, Caido, ZAP, and Invicti as teams demand DAST that runs continuously in CI/CD, AI-powered pentesting, and visibility into code and…
A guide explains how to publish research artifacts on Hugging Face, recommending splitting work into separate components: code on GitHub, model weights in HF Model repos, evaluation data in HF Dataset repos, demos in Spa…
A developer at a service company describes the growing problem of reviewing AI-generated code, noting that while agents now produce high-quality pull requests, the volume overwhelms human reviewers, leading to shallow re…
Stanford researchers developed the STORM method, which uses five expert perspectives to produce 25% more organized research than standard single-shot prompting. The method simulates a panel of experts before writing begi…
Google Cloud CISO Chris Betz and senior director Ruchi Shah detailed how the company uses AI agents to automate software development lifecycle security, including the open-source Mantis framework that reduces token overh…
Chinese open-source model GLM-5.2, released by z.AI under an MIT license, is challenging U.S. AI leaders like Anthropic and OpenAI by offering competitive coding and agentic-workflow performance on a one-million-token co…
A developer applied Specmatic's spec-first approach to TRIO, a multi-agent AI assistant built with FastAPI and React. Contract testing with OpenAPI 3.0 caught mismatches in response fields, status codes, and validation e…