Hands-on with OpenAI Codex Virtual Machine Feature
kevinkern · x · 2026-07-18
The author tried OpenAI's Codex (Tart) feature, which generates isolated macOS virtual machines for testing applications, avoiding the distraction of frequent desktop window flashing. However, each VM currently consumes about 8GB of memory and has noticeable control latency. The author ultimately decided to continue local testing but found the technical approach interesting.
More from coding & agent
- Google launches Gemini 3.5 Flash Cyber for CodeMender, with limited access for governments — GoogleAI · 2026-07-22
- Cursor doubles usage limits across all plans for Grok, Composer and new models — XFreeze · 2026-07-22
- Video-based proof of work is emerging as a feedback layer for coding agents — Vjeux · 2026-07-22
- Salesforce open-sources MCP+ to filter tool output before it reaches agents — msrivastav13 · 2026-07-22
- Anaconda acquires Kilo Code to expand into agentic software development — anacondainc · 2026-07-22
- Poolside’s laguna s 2.1 claims 118B MoE, 1M context, and 78.5% on SWE-bench Multilingual — ben_burtenshaw · 2026-07-22