Show HN: Run multiple instances of Codex(GUI) each with their own auth
A user developed a tool to run multiple instances of Codex (GUI), each with independent authentication, addressing the limitation of single-account usage. This allows users to manage multiple accounts simultaneously within the Codex application.
Background
- Codex is Anthropic's desktop application (GUI) for interacting with their Claude AI model, similar to how ChatGPT has a desktop app. It lets users have AI conversations and use Claude's features locally.
- This GitHub tool (codex-multi-account) lets a user run several separate Codex windows at the same time, each logged into a different Anthropic account. Normally, the Codex app only supports one session per machine.
- The need for this arises because Anthropic currently restricts each Codex instance to one account. Power users who manage multiple accounts (e.g., for work + personal use, or for testing) previously had to log out and back in to switch — or couldn't run multiple instances at all.
- The broader context: as AI assistants become professional tools, users seek the same multi-account flexibility that browsers, Slack, or email clients have long offered. This is a third-party workaround, not an official Anthropic feature.
Max Weinbach says he had early access to OpenAI's new model GPT-5.6 Sol, calling it his favorite model by far. He highlights that it never gives up and will keep reasoning until it's done. OpenAI announced that GPT-5.6 Sol, along with Terra and Luna, will launch publicly on Thursday, with preview access expanding globally now.
The US government ordered Anthropic to suspend access to its Fable 5 and Mythos 5 models for all customers, citing a potential jailbreak technique that involved asking the model to review a codebase for vulnerabilities—a capability Anthropic says is available in other public models. Access was abruptly cut off on June 12.
Andrej Karpathy announces the release of Claude Fable 5, the same underlying model as Mythos but with added safeguards. He calls it a major step forward, particularly for long problem-solving sessions on difficult tasks, and describes it as state-of-the-art on nearly all benchmarks with exceptional performance in software engineering, research, and vision.
Roman Storm warns that the legal theory in his case could set a precedent making open-source developers liable for how others use their code, potentially criminalizing the mere publication of privacy, messaging, or crypto tools. He notes that developer Michael Lewellen cannot publish lawful code due to prosecution fears, and argues this chilling effect extends beyond any single case.
Meta's engineering culture is deteriorating under Mark Zuckerberg and Scale AI CEO Alexandr Wang, who have introduced keyboard tracking, reassignments to data labeling, and AI-centric performance metrics. Critics argue this incentivizes performative AI use, drives away experienced engineers, and contributed to a major Instagram hijacking incident caused by AI-written and AI-reviewed code.