Legal AI is splitting in two—and most people miss the difference

Core Insights - Thomson Reuters announced that CoCounsel has reached one million users across 107 countries and territories, highlighting significant growth in legal AI adoption [1] - Anthropic introduced an expanded suite of enterprise plugins for Claude, including tools tailored for legal, finance, and HR applications, indicating a shift towards specialized AI solutions in the legal sector [1][6] - The recent developments underscore the ongoing evolution in legal AI and the importance of understanding the underlying systems that support these technologies [3][4] Industry Analysis - A recent incident involving a general counsel testing Anthropic's Claude for contract review revealed that the AI pulled information from Wikipedia, sparking debate about the readiness of foundation models for legal work [2][4] - The reactions to this incident were polarized, with skeptics claiming that foundation models are inadequate for legal tasks, while proponents argued that improvements are forthcoming; however, both sides overlooked the critical issue of system architecture [4][5] - The distinction between AI capable of automating workflows and AI that can perform authoritative legal work is becoming increasingly recognized in the market, as evidenced by the stock performance of Thomson Reuters following the announcement of CoCounsel's user milestone [7]