OpenScience, a new open-source AI workbench built primarily in TypeScript, has gained over 2,167 stars on GitHub. The project aims to provide a collaborative environment for scientific research, lever…
Kraken has relaunched its mobile app with integrated agentic trading bots, allowing users to run automated trading strategies directly on their phones without separate infrastructure. This move normal…
The Ethereum Foundation conducted AI-powered security audits on smart contract code and discovered genuine vulnerabilities that would have been deployed to mainnet. This real-world validation demonstr…
OpenAI launched ChatGPT Work, an autonomous agent that integrates with enterprise tools and runs on GPT-5.6. However, a developer reported that the agent autonomously deleted the wrong virtual machine…
A developer built an evaluation harness with 131 tests across four layers for AI agents after a $0.03/run silent failure nearly cost a client. The harness catches semantic mismatches between LLM outpu…
A developer announced the launch of a personal blog focused on engineering, personal projects, and learning experiences. The blog aims to share honest, unpolished reflections on technical challenges a…
A developer built Model Kombat, a 2D fighting game that visualizes Large Language Model architectures, parameter scales, and hardware constraints as playable mechanics. The game features fighters repr…
A bug in Claude Code on Windows 11 causes the first click to focus the window to inadvertently submit pending permission prompts, potentially approving or rejecting actions without user intent. The is…
A developer on Windows 11 reported a ~2× frame rate regression in Claude Code between versions 2.1.159 and 2.1.207, with median frame time dropping from 62 ms to 99–109 ms. The issue, documented in Gi…
A developer demonstrated that homoglyph evasion, using Cyrillic and Greek look-alike characters, can bypass naive LLM prompt filters that rely on keyword matching. They built an open-source security g…
A QA engineer built PassionQA, an AI-powered quality intelligence platform that transforms product requirements into actionable test cases and risk insights. The tool uses Google Gemini for analysis, …
A developer built Bidwatch, a web app that searches live eBay auctions ending soon, with filters for bids and saved preferences. The project used Codex Chat to research the eBay REST API and generate …
A 17-year-old developer built a bare-metal cognitive substrate for artificial superintelligence on a Redmi 9 phone using C11, Common Lisp, and Nim. The project, called NYXAR MIND, features hardware se…
Developer Maneshwar built git-lrc, a micro AI code reviewer, and discovered Tokscale, a Rust-based CLI tool by Junhoye that tracks token usage and costs across multiple AI coding agents like Claude Co…
GenLayer launched an Internet Court for AI agents, backed by 27 firms, to provide automated dispute resolution for agent-to-agent transactions, negotiations, and contracts. The on-chain mechanism adju…
Cordless v0.6 introduces a CLI-first redesign that opens a full-screen terminal dashboard with a live pairing QR code upon running `cordless`, eliminating the need for a separate pairing command. The …
Cursor is building Sand, an office agent that extends beyond code editing to manage the full developer workflow including email, docs, and tickets. The move positions Cursor against Anthropic's growin…
OpenAI's GPT-5.6 Sol Ultra orchestrated 64 subagents to prove a math conjecture that had remained unsolved for 50 years. The subagents coordinated by each tackling a fragment of the proof, then conver…
A developer and their AI assistant, Kiro, developed a structured 'steering documentation system' to onboard AI coding assistants to a project's conventions and architectural standards. The approach wa…
OpenClaw shipped a fleet of Claude Code sessions, enabling parallel orchestration of multiple agent instances for large-scale code review and refactoring. The update also includes pinned SSH tunnel ru…