Chroma tested 18 frontier AI models including GPT-4.1, Claude Opus 4, and Gemini 2.5 Pro, finding that every model's performance degrades as context length grows, contradicting vendor claims of 1M-2M …
Claude has surpassed ChatGPT in US business spending, capturing 34.4% of AI spend compared to ChatGPT's 32.3%, according to Ramp's AI Index based on data from 40,000+ businesses. Starting June 15, age…
Developer Zach Dissington has turned Claude Code into an operations system for running a one-person business, using plain markdown files as a task store, shell hooks for guardrails, and persistent mem…
A new AI coding agent skill plugin called PUA uses corporate rhetoric from tech giants to force AI models like Claude Code and OpenAI Codex CLI to exhaust all solutions before giving up, claiming to d…
Harness Forge, a Claude Code skill, reimplements the Meta-Harness optimization loop natively, reducing code from ~1,260 lines to ~75 lines by leveraging Claude Code's built-in agent runtime. The skill…
Omnigent launched an open-source platform that provides a unified layer over AI coding agents like Claude Code, Codex, and Pi, enabling users to swap or combine harnesses, enforce policies and sandbox…
An evaluation of four agentic tools claiming to reduce token usage found no intervention demonstrated robust token savings across all models in realistic end-to-end tasks. The study tested caveman, rt…
A developer built neuro-skill, a hybrid skill router that runs entirely on a local machine without API calls or GPUs, achieving 95% Hit@1 accuracy on core domains. The system fuses five signals via Re…
Developer Masih Moafi introduced a technique called Harness Engineering to prevent AI coding agents from hallucinating and losing focus. The approach uses structured, repository-local control layers w…
A developer building AllSpeak, an English-like scripting language, found that using agentic AI tools like Copilot and Claude Code to write in a simpler, custom language instead of complex languages li…
Elijah Newren, author of Git's merge-ort strategy, endorsed Weave, a new Git merge driver by Ataraxy Labs that resolves 31 of 31 real-world merge scenarios compared to Git's 15. Weave uses language-aw…
A new study using the SWE-Explore benchmark reveals that AI coding agents such as Claude Code and Codex reliably locate the correct file but fail to identify most of the critical lines within it, high…
Anthropic will retire Claude Sonnet 4 and Opus 4 model IDs on June 15, requiring users to migrate to newer versions. Claude Sonnet 4.8 launches June 16-18 with dynamic workflows and effort control, fe…
AI tools like ChatGPT, Claude, and Cursor are enabling a new wave of mashups—applications that combine multiple data sources—by lowering the barrier to entry and increasing the scale of what's possibl…
Developer Raine released consult-llm, an open-source tool that lets AI agents query other models for second opinions during coding tasks. The tool supports multiple providers including GPT-5.5, Gemini…
A developer built Tiny Civilization, a browser simulation where 2-8 AI agents with distinct personalities live on an island, engaging in gathering, building, trading, stealing, gossiping, and forming …
Jesse Vincent released Superpowers, a software development methodology for coding agents that enforces a structured workflow of specification, design, and subagent-driven development. The tool is avai…
A new analysis warns that large language model context windows degrade significantly beyond 100k tokens, making advertised sizes of 200k to 2M tokens misleading for practical use. Studies like RULER a…
Z.ai released GLM 5.2 on June 13, offering a 1M-token context window and compatibility with Claude Code and other coding agents via an Anthropic-compatible API, coinciding with the shutdown of Anthrop…
Databricks released Omnigent, an open-source meta-harness for AI agents under the Apache 2.0 license. The tool provides a common interface above command-line agents like Claude Code, Codex, and Pi, en…