I vibe coded a programming language, but I'd rather learn C the old way
A developer created a systems language called Tig using AI-driven "vibe coding," but the project stalled after exhausting free tokens. Turning away from AI dependence, they successfully built a lexer for a calculator in raw C by using traditional resources like man pages and YouTube tutorials, concluding that learning to code independently, though slower and harder, is more rewarding.
Background
- "Vibe coding" is a term that recently emerged in tech circles, popularized by OpenAI's Andrej Karpathy. It means building software by prompting an AI (like Claude or ChatGPT) in natural language, without deeply understanding the code being generated — essentially "coding by vibes."
- The poster tried to build Tig, a systems programming language, entirely by vibe-coding. They hit a hard limit when their AI-token budget ran out and they couldn't afford more API credits ("Cascade code" refers to the AI coding assistant Cody/Cascade from Sourcegraph).
- Many junior developers and hobbyists now rely on AI as a crutch, generating large projects without learning fundamentals. The post's moral — that grinding through C tutorials and writing code by hand, no matter how slow, builds genuine skill — reflects a growing backlash against AI-dependent development.
- "Man programs" (man pages) are the built-in Unix/Linux documentation system: terse, old-school, no AI needed.
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.