Full-text search across 70055 articles. Combine with topic and date filters; results sorted by relevance.
A study of run-to-run consistency in web-search-enabled LLMs found that about 31% of recommended businesses changed when the same "best X for a small business" question was asked again minutes later, based on 60 response…
A developer has published a practical guide for engineers rolling back a first AI-generated pull request, arguing that a rollback plan should be prepared before any agent-authored code is merged. The guide recommends hal…
A repository called zero-trust-llm released AGENTS.md, a master operational ruleset that forces LLM agents through a five-step loop — [HYPOTHESIS], [IDENTIFY REQUIRED EVIDENCE], [GROUND VERIFICATION METHOD], [EXECUTE], a…
A developer built a bilingual, multi-channel AI calling and chat agent that routes phone, web chat, WhatsApp, and Instagram traffic through a single RAG pipeline backed by ChromaDB and gemini-embedding-001. The system us…
Alex Ziskind built a four-GPU workstation with 384GB of VRAM using four RTX Pro 6000 Blackwell cards and a 32-core Threadripper Pro 9975WX, and measured that 71% of every coding-agent turn never touches the GPUs, conclud…
A security analysis found that nearly one in ten internet-facing LiteLLM gateways were running with the literal example admin key 'sk-1234' from the documentation still active, exposing provider API keys, prompt logs, an…
A developer published a model-neutral Pi extension that displays live throughput metrics—time to first token (TTFT), decode tokens per second, and a client-side prompt-rate estimate—in the coding agent's status footer. T…
A developer maintains Weftgate, an open-source verification gate for coding agents that checks environment-variable reads, dependency imports, and FastAPI route references against repository contracts. The tool runs loca…
Maycon, a Systems Analysis and Development student at UNICID, is transitioning from a career in customer service, sales, and paid traffic management into software development. He has completed more than 30 courses and ha…
AgentsDock released version 0.2.12, a macOS 14+ universal IDE for agentic AI research that supports Claude Code, Codex, and Cursor in one desktop and mobile workspace. The tool connects remote workstations, Mac minis, an…
AgentRuleBench, an open-source benchmark released alongside the archprint architecture-rule mining tool, found that AI coding agents did not violate an inferred architecture rule across a pilot spanning three vendors' ag…
A developer ran six Codex coding-agent executions of a Java String Calculator kata, varying the underlying model (Sol, Terra, Luna) and reasoning effort, to study how agents, a repository skill, and the Seed4J CLI intera…
A developer argues that enterprise AI governance must be runtime and deterministic, positioning their SAFi harness as an alternative to agentic frameworks like Claude Code. In SAFi, the LLM is treated as a substrate rath…
A Thai AI practitioner's comparative analysis finds that locally trained Thai language models outperform global frontier models on Thai-specific tasks such as document and handwriting recognition, legal citation, Isan di…
Anthropic engineers David Soria Parra, Justin Spahr-Summers, and Mahesh Murag created the Model Context Protocol (MCP), an open standard introduced in 2024 to connect AI assistants to external data systems and tools, sol…
OpenAI published a case study on Cognition's Devin using GPT-6 Astra to autonomously test its own code, with one AI-generated summary claiming the model reduces engineers' manual review burden by 20–30%. The post present…
A developer built a 5-layer, 512-wide TinyStories language model that runs natively on Apple's M4 CPU by treating ARM Neon instructions—including XOR, popcount, and SDOT—as trainable architectural primitives rather than …
A developer detailed Cordis, an MIT-licensed TypeScript meta-framework that enables runtime hot-swapping of plugins with zero process restarts and zero memory leaks. The framework, originally built for the Koishi chatbot…
Researchers released Benchmark Radar, a living database and search engine for AI benchmarks that catalogs 1,283 source records drawn from 4 benchmark catalogs and 12,916 numeric observations on 790 records. The system dr…
Salesforce will host a dedicated security keynote, "Trust Across Agents, Data, and Platforms," on September 15 at 2:15 PM PT at Dreamforce 2026, alongside more than 30 security-focused sessions, as the company positions …