The AGENTS.md file in the Ghostty repository provides guidelines and instructions for AI agents and automated tools contributing to the Ghostty terminal emulator project, outlining expected behavior, coding standards, and communication protocols.
Background
- Ghostty is a popular open-source, GPU-accelerated terminal emulator written in Zig, designed for speed and modern features.
- This AGENTS.md file is a special-purpose document that instructs AI coding agents (like GitHub Copilot or Cursor) on how to behave when working on the Ghostty codebase.
- It tells the AI things like: which language to use, which patterns to follow, how to handle errors, and what style conventions the project expects.
- The file exists because AI agents are increasingly used to generate or modify code, and projects need a way to set guardrails so the AI doesn't write code that breaks the project's conventions.
- This is notable because it signals a shift in open-source maintenance: instead of just writing docs for humans, maintainers now also write docs specifically for AI agents that will contribute code.
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.