We moved a whole codebase onto TypeScript with a fleet of subagents
The article describes how the company migrated an entire JavaScript codebase to TypeScript by deploying a fleet of AI-powered "subagents" to automate the process, significantly reducing manual effort and time compared to a traditional manual migration.
Background
The article describes an experiment by startup Cirrcles (a community-driven commerce platform). They migrated a large JavaScript codebase to TypeScript using a "fleet" of AI subagents — small, narrowly-focused AI tasks that each handled one file, coordinated by a parent agent — rather than doing it manually or with a single LLM prompt.
- **TypeScript** is Microsoft's typed superset of JavaScript; it catches bugs at compile time and is standard in professional web development.
- Migrating real codebases to TypeScript is tedious and error-prone (thousands of files, implicit types, edge cases). Most teams do it by hand.
- Using coordinated AI subagents is novel and shows a practical, non-hypothetical use of LLMs to automate a gnarly software-engineering task, hinting at a future where developers orchestrate AI workers rather than write everything themselves.
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.