Disney is dropping Microsoft's GitHub Copilot and several other AI coding tools in the US in August, according to an internal message viewed by Business Insider, and plans to adopt OpenAI's Codex codi…
Medley, a harness system that orchestrates model workers with planning, routing, and acceptance stages, achieved the highest reported results on four public benchmarks: Terminal-Bench 2.1 (93.25% task…
OpenAI engineers detailed how ChatGPT and Codex optimize their agent loop across three layers — harness, API, and inference — to reduce cost per successful task. The harness layer cuts repeated work w…
ConardLi's garden-skills project ships production-ready Agent Skills for AI coding agents like Claude Code and Cursor, encoding taste and process discipline rather than raw capability. The skills incl…
Confluent announced Confluent Platform 8.3, built on Apache Kafka 4.3.0, which includes Confluent Platform for Apache Flink 2.4.0 with an MCP server for AI agent integration, user-defined functions, a…
Loop engineering, a technique where an AI model is called repeatedly in a loop to decide whether to continue, is being marketed as a product category by AI infrastructure vendors, but it is actually a…
Sightmap, an open YAML format and CLI stewarded by Fullstory's Subtext team, provides runtime context for AI agents by maintaining a shared memory of a web app's views, components, and API requests. T…
Codex will restore a five-hour usage limit tomorrow after temporarily pausing it while investigating why GPT-5.6 Sol was consuming usage faster than expected. Codex says it has landed several improvem…
Job Finder India, an open-source command-line tool by developer Harsh Garg, scores jobs 0–5 against a user's résumé and tells candidates when not to apply, treating seniority or function gaps as disqu…
OpenAI has opened applications for the OpenAI Student Collective, a yearlong program that funds and supports undergraduate students leading AI learning, projects, and events at their universities. The…
Serhii Korniienko released Bullshit Detector, a set of open-source agent skills that fact-check viral YouTube videos, articles, tweets, and PDFs by producing a claim-by-claim verification report with …
OpenAI's agent harness, the technology underneath its Codex coding agent, has been optimized to slash token costs by up to 80%, according to an exclusive interview with OpenAI engineers. The harness n…
OpenAI published an exploratory field report on July 28 covering eight agent-assisted scientific-computing projects, mostly in life sciences, finding that coding agents accelerated maintenance, migrat…
Prime Intellect has integrated 23 agentic tasksets into a unified API, providing approximately 365,000 tasks for software engineering, terminal, and search domains, ready for reinforcement learning tr…
According to Skillselion, a directory of Claude Code, Codex and Cursor extensions, the ten most-installed Claude Code skills come from exactly three authors: Matt Pocock (five skills), Vercel Labs (fo…
A developer who burned through their token budget running Claude Code and Codex found that local inference with open-weight models trades dollar costs for wall-clock and retry costs. Testing Qwen3-Cod…
JetBrains released Rider 2026.2 on July 22, introducing Agent Skills that expose IDE analysis capabilities—profiler data, coverage maps, refactoring intelligence, and framework knowledge—directly to e…
OpenAI reset usage limits and lifted the five-hour cap for ChatGPT Plus, Business, and Pro subscribers after GPT-5.6 Sol drained allowances faster than expected, with product lead Thibault Sottiaux an…
The marginal cost of AI inference will approach zero as open models rival frontier models, reshaping the business models of labs like OpenAI and Anthropic toward low-margin inference sales, according …
Agent Island, an open-source status companion for Claude Code and Codex, clarifies that Claude Desktop, Claude Code, and provider usage are separate state machines on Windows. The project warns agains…