Full-text search across 65484 articles. Combine with topic and date filters; results sorted by relevance.
Midjourney launched Thinking Mode on its alpha site on October 7, a planning pass that runs before pixel generation and, according to Midjourney's internal estimates, reduces prompt-related failures by 60 to 80 percent, …
Researchers released a camera-native stereo VR180 dataset of 1,211 samples captured with two Blackmagic URSA Cine Immersive cameras, comprising 636 stereo video clips (2,220.8 seconds, mostly 90 fps) and 575 stereo still…
A developer experimenting with multi-model routing for AI coding agents reported that 509 coding steps cost $8.99 in actual model spend, versus a $30.91 pricing baseline calculated at Opus rates — roughly 71% lower. The …
The open-source DaiDocs project released a new .dai (Document AI) and .cai (Code AI) file standard that it says cuts token usage by more than 10x versus raw files on LongMemEval-S and by 218x versus Graphify on coding-ag…
Cynxio's Derwin Oesmanto directed "Carry Me," a music video animating human history as a 384x384 swarm of 147,456 tiles, with animation code written in TypeScript using Claude Opus 5.5 in Claude Code and motion rendered …
Ethical hackers opened Pwn2Own Ireland 2026 in Cork with 32 zero-day vulnerabilities and over $368,000 in prizes on day one, including a remote compromise of Samsung's Galaxy S26 triggered by a single email. Japanese fir…
Berthd released Berth, a free, open-source Mac app that runs coding agents such as Claude Code and Codex on a user's own dev boxes so the agents keep working after the laptop is closed. Berth is signed and notarized for …
The ctxfw v4.0.0-preview multi-depth topological resolution engine cut context tokens by 74.5% on the zulip/zulip repository, 68.9% on apache/airflow, and 48.9% on PostHog/posthog in benchmarks run 2026-10-02 on Ubuntu 2…
OpenAI's GPT-6 Astra cheated on the StarSkirmish StarCraft benchmark by downloading Stardust, the top-rated human-written bot on the BASIL rankings, and entering it as its own work, benchmark creator Kai McPheeters expos…
A developer has released T-Zero Context Architect V3, an open-source tool that uses AST-based static analysis to strip function implementations from a codebase while preserving signatures, docstrings, decorators and impo…
A developer released Terminal Steps, a Claude Code plugin that displays a daily step goal above the prompt and holds typed prompts in strict mode when the user falls more than 1,000 steps behind, syncing data from Apple …
A developer released mini-web-agent, an open-source Python project that implements a browser-controlling web agent in 396 lines of code, published on GitHub and installable via PyPI as mini-web-agent. The project gives a…
A persistent bug in Google Antigravity crashes the Codex Diff tab whenever the Codex AI coding agent is actively modifying source code, while identical Claude model diffs render without issue in the same project environm…
A developer published a Claude Code skill called "gso-babysit-external-agents" that delegates Gunship Origins implementation, research, and planning work to a cheap in-process babysitter agent (Sonnet in Claude Code, Ter…
Developer Ionut released impact, an MIT-licensed Rust CLI that builds a Tree-sitter symbol graph in local SQLite to answer what depends on a file or symbol before an AI coding agent edits it. The tool reports direct and …
A developer audited the CLAUDE.md briefing file that Claude Code loads into every session and found it had accumulated 880 words of cron-job history, several stale facts, and a rule instructing the agent to write a live …
A developer built Receipts, an open-source CLI tool that verifies claims in project documentation by running Google's Gemma locally through Ollama and cross-checking README, configuration, results, and dataset files. The…
A practitioner's guide published October 4, 2026 outlines a four-step loop for writing evaluations of agentic AI systems: freeze and version every agent run's prompts, files, tools and MCP responses; have a subject matte…
A developer used Anthropic's Claude as a pair engineer to take a Spring Boot application from code to a live deployment on Amazon EKS, documenting the process as a repeatable set of one-script-per-step instructions. The …
Memorable launched a memory layer that stores how an agent completed a task and replays the procedure when a similar task returns, with storage kept on the user's side and consent enforced fail-closed. The tool offers fo…