Anthropic and OpenAI Tighten Controls on AI-Assisted Decompilation
cnBeta reports that Anthropic updated its real-time cybersecurity classifier to block automated decompilation performed through the community-developed "everything decompiles" (REA) framework. The report also attributes to other reporting that OpenAI banned relevant accounts under network-abuse policies, though it names no accounts and provides no direct OpenAI confirmation. The same report says Anthropic quietly added a non-disableable rule on October 27 permitting original games and games based on users' own designs and assets while prohibiting replicas of specific existing games, and that some users have shifted toward locally deployed or open-source AI tools for reverse-engineering work.
The report frames the tightening as a response to AI-assisted reverse engineering lowering the barrier for browser ports and game remakes while raising cybersecurity risk, and it argues AI agents attack public infrastructure faster than patches can be issued. It also notes that many low-quality recompilations and browser ports depend on the restricted tools, so the report says that surge may already be slowing.