Livelymerge is a system designed to merge and reconcile conflicting changes in structured documents, such as JSON data, by letting users visually inspect, understand, and resolve differences interactively. The experiment explores how to make merging more human-friendly and less error-prone compared to traditional text-based diffs.
Background
Ink & Switch is a research lab that explores new tools for creative work, especially around digital documents and collaboration. Livelymerge is one of their experimental projects. It tackles a familiar pain point: when two people edit the same document and then try to merge their changes, tools like Google Docs or Git show you text-level differences but not *why* the changes were made — the reasoning, the back-and-forth, the context. Livelymerge prototypes a system that records more of that collaborative context (discussions, decisions, alternatives considered) and replays it in a "lively" way, so the person merging can understand not just what changed but what motivated the change. The project is squarely in the "digital tools for thought" space, similar to work by researchers like Andy Matuschak or the Dynamicland group. The article describes the experiment's design goals, the technical approach, and lessons learned from building it.
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.