Full-text search across 70055 articles. Combine with topic and date filters; results sorted by relevance.
A developer at Vstorm built AgenticOS, an open-source project for creating and using AI agents, and detailed how its Tauri desktop app renders and animates five interactive desktop pets. The pets use layered sprite grids…
OpenAI released GPT-6 Astra, a high-capability model for complex reasoning, coding, computer use, and document creation, featuring a 1,050,000-token context window, 128,000 max output tokens, and new API capabilities for…
A new tool called Spm lets developers declare AI skills as git dependencies in an ai.json file, pinning them by tag, branch, or commit and locking them to an immutable SHA in ai.lock. Spm materializes those skills for Am…
Microsoft announced Project Zenith on September 4, a new Windows developer hardware class requiring a minimum 64GB of unified memory and 250GB/s of memory bandwidth to run 30-billion-parameter AI models locally without a…
Researchers proposed TEAM-Design, a rule that assigns every task two replay probabilities — one per baseline — to decide under a fixed replay budget whether a human-AI workflow should be kept over the human alone or the …
A developer discovered that 71 of the 223 keys in Claude Code's settings reference are scope-restricted, meaning placing them in a project's .claude/settings.json silently does nothing — no error, no warning. The develop…
Anthropic has listed Growomat, a hosted MCP connector that has run since June, in the Claude connectors directory, replacing the previous setup that required users to copy and paste the URL https://mcp.growomat.com/mcp i…
Anthropic's Global Head of Public Sector Teresa Carlson announced at the Billington Cybersecurity Summit that the company's Fable 5.1 model is now available on its Claude for Government platform, with more public-sector …
Contextify has released Contextify for Windows, a tray app that indexes Claude Code and Codex session history in the background and provides command-line access via contextify.exe, with optional Cloud sync for cross-devi…
X. Eyee, a partner at Offline Research and former engineering lead at Google and Microsoft, said on CNBC that the AI industry's celebration of artificial general intelligence uses a definition that 'leaves most of humani…
CrowdStrike announced Agentic Identity Provider (Agentic IdP) in Falcon Next-Gen Identity Security at Fal.Con 2026, giving AI agents cryptographically verifiable identities and brokering short-lived, least-privilege acce…
OpenAI announced a solution to the Navier-Stokes Millennium Prize problem, fully formulating its results in the Lean proof assistant, according to a post by the company. Hours earlier, Tristan Buckmaster posted about sep…
A new engineering essay argues that teams should move operational workflows into Slack by building thin bots that route commands to internal tools, rather than relying on ad hoc AI conversations for tasks like restarting…
A developer found that a single LLM evaluation case in their regression suite fluctuated from 5/5 to 2/5 and back without any code or prompt changes, revealing that the eval's measurement was noisy. To address this, they…
AI output is accelerating faster than human review can adapt, shifting the bottleneck from generation to verification, according to engineering teams and researchers. OpenAI claims an unreleased model resolved the Navier…
Inception released Mercury 2.5, which it calls the most capable diffusion LLM on the market and the largest it has ever trained, reporting a 40% intelligence gain over Mercury 2 at 1,107 tokens per second on widely avail…
Vdr, a secure-by-design Linux core dump handler written in Rust, is seeking review, claiming to eliminate the CVE-2022-4415 class of vulnerabilities by using 0600 root-only file permissions and avoiding ACL code. The han…
Quidli launched Connect, an open payments system that lets AI agents send tokens to people or other agents by resolving social handles from Telegram, Discord, Farcaster, X, GitHub, LinkedIn, email, and phone to wallets, …
A developer argues that AI coding agents need explicit runbooks, not general rules files, to handle risky operations like deployments safely. The post provides a template with preconditions, STOP conditions, verification…
IBM's coding agent Bob is designed to write Java, leveraging the language's 30-year history as a stable foundation and a rich source of training data for AI, according to Markus Eisele on the Stack Overflow podcast. Eise…