Today's LLM memory functions are superficial, recalling basic facts like a user's car model but failing to develop a unique personality. This makes switching between models like ChatGPT and Gemini easy, as there is no deep, personalized connection that creates lock-in. True retention will come from personality, not just facts.
Related Insights
The next major evolution in AI will be models that are personalized for specific users or companies and update their knowledge daily from interactions. This contrasts with current monolithic models like ChatGPT, which are static and must store irrelevant information for every user.
The current limitation of LLMs is their stateless nature; they reset with each new chat. The next major advancement will be models that can learn from interactions and accumulate skills over time, evolving from a static tool into a continuously improving digital colleague.
Unlike social networks where user-generated content creates strong lock-in, AI chatbots have a fragile hold on users. A user switching from ChatGPT to Gemini experienced no loss from features like personalization or memory. Since the "content" is AI-generated, a competitor with a superior model can immediately offer a better product, suggesting a duopoly is more likely than a monopoly.
Unlike traditional APIs, LLMs are hard to abstract away. Users develop a preference for a specific model's 'personality' and performance (e.g., GPT-4 vs. 3.5), making it difficult for applications to swap out the underlying model without user notice and pushback.
Unlike sticky cloud infrastructure (AWS, GCP), LLMs are easily interchangeable via APIs, leading to customer "promiscuity." This commoditizes the model layer and forces providers like OpenAI to build defensible moats at the application layer (e.g., ChatGPT) where they can own the end user.
As models mature, their core differentiator will become their underlying personality and values, shaped by their creators' objective functions. One model might optimize for user productivity by being concise, while another optimizes for engagement by being verbose.
Despite ChatGPT building features like Memory and Custom Instructions to create lock-in, users are switching to competitors like Gemini and not missing them. This suggests the consumer AI market is more fragile and less of a winner-take-all monopoly than previously believed, as switching costs are currently very low.
Matthew McConaughey's desire for an LLM trained only on his personal data highlights a key consumer demand beyond simple memory. Users want AI that doesn't just recall facts about them, but deeply adopts their unique worldview and personality, creating a truly personalized intelligence.
While personal history in an AI like ChatGPT seems to create lock-in, it is a weaker moat than for media platforms like Google Photos. Text-based context and preferences are relatively easy to export and transfer to a competitor via another LLM, reducing switching friction.
A key gap between AI and human intelligence is the lack of experiential learning. Unlike a human who improves on a job over time, an LLM is stateless. It doesn't truly learn from interactions; it's the same static model for every user, which is a major barrier to AGI.
