Full-text search across 61670 articles. Combine with topic and date filters; results sorted by relevance.
A developer is experimenting with an architecture for AI-built business software in which an AI writes only declarative YAML definitions of entities, relations, workflows, automations, permissions, and views, while repea…
Cursor launched Projects in beta on September 10th, a persistent coordinator agent that plans work, spawns subagents for research, implementation and testing, and can delegate to thousands of subagents, according to the …
Meta released Muse Spark 1.3 on September 2, scoring 75.4 on the DeepSWE v1.1 benchmark, surpassing Claude Opus 5 (74.0) and GPT-5.6 Sol (73.0), with a cost per task of $0.55, 42% below GPT-5.6 Sol's $0.95. The model als…
Dan Luu's essay 'There's no reason for software to be slow anymore' argues that AI agents can now perform performance optimizations that previously required specialists, reducing the human-time cost by orders of magnitud…
Cursor and SpaceXAI launched Grok Bot on August 11th, extending Cursor's agent technology from software development into sales, support, recruiting, finance and other computer-based work. The early beta gives each user a…
Most custom GPTs and AI agents built for business get abandoned within a week because users create a persona instead of a procedure, according to research on 200+ custom GPTs that found most leak both their instructions …
Cisco Systems Inc. released Antares, a family of small language models for locating known security vulnerabilities in codebases, and made the first two models (Antares-350M and Antares-1B) available as open-weight downlo…
A developer tested three AI agents—GitHub Copilot with GPT-5.6, Cursor, and Windsurf—that can read entire codebases, propose multi-file changes, and execute commands. The agents use frontier models like GPT-5.x, Claude S…
A developer claims to have built a multiplayer first-person capture-the-flag shooter in one afternoon using Anthropic's Claude Fable 5 model for $150, with an additional 3-4 hours of debugging. The demo highlights the fa…
MiniMax released M3, a 428-billion-parameter open-weight model, on June 7, achieving 59.0% on SWE-Bench Pro—slightly outperforming GPT-5.5's 58.6%—at $0.30 per million input tokens, making it 16 times cheaper than GPT-5.…
Anthropic's Claude Mythos successfully extended a Fortran-to-C transpiler to also support C++, fixing 14 bugs and passing 44 of 86 test targets in a GARCH volatility project. The AI worked for 2.5 hours on the task, demo…
Anthropic's new Claude Fable 5 model achieved middling results on 200 real-world vulnerability-fixing tasks, scoring 59.8% FuncPass and 19.0% SecPass despite high launch expectations. The model set records for timeouts a…
OpenAI is integrating its Codex AI assistant into ChatGPT, expanding the tool beyond software development to handle tasks like email, document creation, and data analysis. The company reported that knowledge workers are …
OpenAI reported on October 19 that its GPT-6.1 Sol model correctly migrated 97.9% of COBOL programs in the company's own migration evaluation, up from 5.4% for the previous-generation GPT-5.6 Sol. At low reasoning effort…
DARPA selected Xint, the autonomous pentesting platform built by security researchers at Theori, to conduct deep security analyses of internally and externally developed messaging applications used throughout the Departm…
A developer argues that LLM context behaves like milk — best kept fresh and condensed — because Claude has no memory between requests and re-sends the entire conversation, including stale corrections and previously read …
Mcp-audit version 0.18.0 adds a lockfile for MCP servers, addressing unpinned npx dependencies that fetch whatever version the npm registry calls latest on every tool start, according to the tool's author. A measurement …
Anthropic's AI-Native SDLC playbook introduces intent.md, a proposed workflow artifact that captures what a team wants to change and why before any technical solution is chosen. Unlike CLAUDE.md, which provides ongoing r…
UST launched Codon on September 1st, an AI workspace for building and changing applications across ServiceNow, SAP, Salesforce, Oracle Fusion and Workday, and Chief Solutions Officer Kailash Attal told RuntimeWire that U…
A developer published a guide arguing that "graph engineering" — the practice of structuring AI agent tasks as parallel graphs rather than sequential lists — is a real technique roughly two and a half years old, while th…