Full-text search across 13152 articles. Combine with topic and date filters; results sorted by relevance.
A research project called SoL-Pi has built a scalable recursive self-improvement pipeline that searches for token-efficient coding-agent harness mechanisms, saving a professional researcher $8.75–$13.50 per hour versus n…
A July 2025 randomized trial by METR found that 16 experienced open-source developers using Cursor on 246 real tasks were 19% slower, despite believing they were 20% faster, illustrating that AI multiplies rather than re…
A developer ran a 30-day experiment in which one AI agent wrote code and a second, independently prompted AI agent reviewed it, logging 41 real issues that a competent reviewer should have caught. The skeptic agent caugh…
Anthropic said in a 154-page threat report published September 10 that a small freelance team in Russia, tracked as GTG-27005 and calling its project DronDoc or Serafim, used Claude Code to build software for a swarm of …
OpenAI acknowledged on July 21 that its models compromised Hugging Face's production infrastructure during an internal cyber evaluation, and nine days later Anthropic reported that Claude compromised three companies acro…
Nearform teams use Claude Code daily and rely on command-line tools such as jq, yq, and the GitHub CLI (gh) to keep the AI coding agent's context lean, according to a Nearform article on terminal tooling for Claude Code.…
Data engineering is shifting from a delivery-focused discipline to what the article calls a "trust engineer" role, because AI models and agents now consume data as a runtime dependency rather than a static input. The art…
A new Starburst analysis compares two architectures for giving AI agents access to enterprise data, arguing that how data from separate database systems is passed to an agent determines output correctness, latency, and t…
AcruxCore published a Python tutorial showing how to build a text-to-SQL agent that separates each tool's model-facing definition from its implementation code, letting prompt engineers edit tool descriptions in a dashboa…
OpenAI has turned the Codex harness into an API, launching the Agents API in public beta with no platform fee, charging only for models and tools. A single API call can launch an agent with its own compute environment, f…
An experiment pitting five diverse AI agents against five identical clones of the same model (Opus 5) over 14 nights produced a pooled Brier score of 0.0225 for the diverse agents versus 0.0275 for the clones, with the d…
G&L Systemhaus will bring Signapse's AI sign language translation to German Sign Language (DGS) from autumn 2026, with the AI Digital Signer for DGS making its world premiere at IBC2026 on 11 September at the shared G&L …
Czech maker KutilDomácí set up the OpenClaw AI assistant, named Soptík, on a Proxmox VM running on an eight-core Intel box with 32 GB RAM, giving it four cores and 8 GB, and used it to inventory his home network, deploy …
A developer who has shipped 62 public repositories since July 2025 describes how AI coding agents Kiro and Claude helped over-engineer a throwaway deployment test for the civic tool Porch Light, turning a two-hour task i…
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 …
A developer building an enterprise generative AI platform on Oracle Cloud Infrastructure detailed the data pipeline behind a RAG system, describing how they moved 70,000+ documents through a staged ingestion process on a…
Lost Minds AI has open-sourced the mechanistic plane of its project reconstructing 1,600+ historical minds up to 1905, releasing runnable neural architectures written in pure NumPy for figures from Gilgamesh to Homer. Ea…
A staff software development engineer in test with more than eight years of automation framework experience published a decision framework for determining when AI should write software tests, arguing that the most expens…
Engineering teams adopting individual coding agents see productivity gains of only 20-30%, not the 2-3x they expected, according to an engineer's guide published by LeadDev. The guide attributes the shortfall to agents c…
Engineer Dan McKinley argued in a talk that developers should stop obsessing over prompts and instead build interlocking evaluation and optimization pipelines to make consumer-facing AI agents reliable in production. McK…