Abram Demski reports using Claude Opus 4.8 and GPT 5.5 to conduct 'vibe research' on logical induction as a model for AI trustworthiness and recursive self-improvement, collaborating with Anson Berns …
A developer released okf-skills, an open-source toolchain that implements the Open Knowledge Format (OKF) for Claude Code and other coding agents. OKF provides structured, versioned, and portable proj…
Andrew Ambrosino, lead of OpenAI's Codex desktop app, says nearly 100% of OpenAI employees now use Codex weekly and aims to make it the best desktop app ever. In a podcast, he discusses how AI flips p…
A GitHub issue requesting a feature to exclude sensitive files from OpenAI Codex remains open as of August 2025. The feature would allow users to specify files and paths that the AI agent must not rea…
OpenAI added the GPT-5.6 family to its Codex repository in a commit on June 26, 2026, updating the codebase with 2 commits across 4 files. The change was contributed by a single developer, marking a n…
OpenAI is preparing upgraded controls for its Codex AI assistant that would allow it to operate Microsoft Excel and PowerPoint through dedicated add-in layers, rather than generic screen-clicking. The…
OpenAI is testing a feature that would let Codex users gift credits to others, as indicated by a hidden widget and a new Gifts entry on user profile pages. The feature would revise OpenAI's current te…
AI-powered agents are now reliably orchestrating hacking tools autonomously, finding vulnerabilities that traditional tools miss, while open-weight models with stripped safety guardrails enable unrest…
Cerberus, a local-first security gateway for AI coding agents, intercepts every tool call before execution, risk-scores it across four signals, and allows, audits, asks for human approval, or blocks i…
AI Berkshire, a set of investment research skills compatible with Claude Code and Codex, systematizes the methodologies of value investors Warren Buffett, Charlie Munger, Duan Yongping, and Li Lu. The…
SpinnerRecruit launches a CLI-based job advertising platform that displays targeted ads in AI wait states, paying developers 50% of revenue per impression. The tool integrates with tmux and Claude Cod…
ARA Labs released the Agent-Native Research Artifact (ARA), a toolkit that makes AI-generated scientific research verifiable and auditable by structuring documentation and providing agent skills for c…
OpenAI Codex's record-and-replay feature enables users to automate repetitive computer tasks by capturing workflows as intent-based code rather than raw pixel coordinates. The system generates executa…
Peek-CLI, an open-source tool that lets AI coding agents capture screenshots of browser tabs via a WebSocket daemon and Chrome extension, has been released. The tool works with Claude Code, Codex, and…
Adrafinil, a macOS menu bar app, keeps a Mac awake only while AI coding agents have active sessions, preventing sleep during clamshell mode. It uses a privileged helper for root-level sleep control an…
Boris Cherny of Anthropic, Peter Steinberger, and Addy Osmani of Google are promoting 'loop engineering,' a workflow where developers design automated loops that prompt AI agents instead of typing pro…
OpenAI released GPT-5.6 Sol, its strongest cyber model yet, which is competitive with Anthropic's Claude Mythos Preview on ExploitBench while using one-third of the output tokens. The launch marks a s…
Developer released ai-whisper v0.7.0, an open-source terminal tool that pairs AI coding agents like Claude and Codex in structured workflows to improve code quality through collaborative review. The t…
OpenAI previewed GPT-5.6, a new model family led by Sol, alongside Terra and Luna, with Sol setting a new state of the art on Terminal-Bench 2.1 for agentic tasks. The rollout is limited to trusted pa…
A developer built TokenBoard, a local CLI tool that tracks AI coding token usage from Codex without uploading prompts or code. The tool provides aggregate metrics and a leaderboard for developers to c…