OpenAI Is Developing a ‘Persistent’ AI Agent
Code reviewed by WIRED reveals the company is developing a feature that enables Codex to continue working proactively until it is “put to sleep.”
Topic Memory
Current signal 52.5 with 670 archived momentum points.
Cluster
Code reviewed by WIRED reveals the company is developing a feature that enables Codex to continue working proactively until it is “put to sleep.”
OpenAI is preparing a second $400 million venture fund, far larger than its original $175 million vehicle, according…
Code in the Codex desktop client reveals a dormant allowance system internally called ChatPass that could let applications consume separately metered portions of a user's subscription.
Cybersecurity researchers have disclosed details of a vulnerability in Amazon Kiro, an artificial intelligence (AI)-powered, agentic integrated development environment (IDE), that could facilitate data exfiltration via prompt injection and Kiro Powers.
OpenAI's $230 controller turns recent assistant messages into the asteroids, bricks and food inside three undocumented games.
Discover how loveholidays uses OpenAI Codex to make software development accessible across the business, helping teams turn ideas into products faster.
Particle’s new podcast intelligence platform transcribes and analyzes more than 130,000 podcasts, making their conversations searchable on the web and accessible to AI agents through an API and MCP.
Software delivery platform provider Harness Inc. today announced the launch of Agent-Ready Harness Code Repository and AI Code Review, aimed at developer teams adopting artificial intelligence coding agents at an ever-increasing pace.
AI coding company Replit is throwing its weight behind the model-routing trend by making its “intelligent model routing” system the The post Replit’s new default: Auto mode picks the best model for each task appeared first on The New Stack.
Read-only SQL and code mode let coding agents answer questions across your traces without paging thousands of spans through model context. The post Arize Phoenix has a built-in MCP server that lets your agents query traces with SQL appeared first on Arize AI.
Cursor now runs through the AI SDK harness layer via @ai-sdk/harness-cursor, using the same HarnessAgent interface as every other supported harness.
Researchers have uncovered a critical security flaw in Amazon’s Kiro AI-powered IDE that allows attackers to exfiltrate sensitive local data via prompt injection. The weakness […]
Regulated enterprises and governments can now run holistic AI governance for LLMs and MCP from inside their own environment, including fully air-gapped Mumbai, August… The post WSO2 Makes AI Workspace Self-Hostable, Giving Enterprises and Governments a New Governance Layer for Sovereign AI appeared first on India...
This release adds an MCP server for working with scans and issues from your preferred AI client, and makes Burp AI available to all Cloud customers. Work with Burp Suite DAST from your AI client Conne
OpenAI’s new ChatGPT Admin plugin lets workspace admins manage users and permissions, analyze usage, and build reports directly from a conversation. Here are the details.
Image search on one client site ran at 64% of web's impressions and 11% of its clicks, and no tool in the stack could see it. The new GSC MCP update ships 8 free image SEO tools that read that surface and audit the pages behind it.
“100% of my code is written by [insert whichever AI coding agent is popular right now]!”You’ve probably heard this claim many times this year.
See how Replit built their agents atop LangGraph and integrated LangSmith to pinpoint issues, improve the performance of their agents, and enable human-in-the-loop workflows.
Lovable is branching out from AI-powered web app creation and into MCP-powered ‘capabilities’. We talk to CTO Fabian Hedin.
Say a test starts failing and a developer hands it to a coding agent. It digs into the relevant files, The post When AI agent traces become application data appeared first on The New Stack.
The MCP maintainers published an updated roadmap. Since March, MCP went stateless (no more session handshakes), turned Tasks into an official extension for long-running work, and shipped enterprise auth pieces like issuer validation and Client ID Metadata Documents.