Even with access to user data from apps like Gmail, LLMs are struggling to deliver a deeply personalized, indispensable experience. This indicates that the challenge may be more than just connecting data sources; it could be a core model-level or architectural limitation preventing true user context lock-in and a killer application.
Related Insights
Current LLMs are intelligent enough for many tasks but fail because they lack access to complete context—emails, Slack messages, past data. The next step is building products that ingest this real-world context, making it available for the model to act upon.
![[State of RL/Reasoning] IMO/IOI Gold, OpenAI o3/GPT-5, and Cursor Composer — Ashvin Nair, Cursor thumbnail](https://assets.flightcast.com/V2Uploads/nvaja2542wefzb8rjg5f519m/01K4D8FB4MNA071BM5ZDSMH34N/square.jpg)
General LLMs are optimized for short, stateless interactions. For complex, multi-step learning, they quickly lose context and deviate from the user's original goal. A true learning platform must provide persistent "scaffolding" that always brings the user back to their objective, which LLMs lack.
People struggle with AI prompts because the model lacks background on their goals and progress. The solution is 'Context Engineering': creating an environment where the AI continuously accumulates user-specific information, materials, and intent, reducing the need for constant prompt tweaking.
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.
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.
Moving beyond simple commands (prompt engineering) to designing the full instructional input is crucial. This "context engineering" combines system prompts, user history (memory), and external data (RAG) to create deeply personalized and stateful AI experiences.
AI struggles to provide truly useful, serendipitous recommendations because it lacks any understanding of the real world. It excels at predicting the next word or pixel based on its training data, but it can't grasp concepts like gravity or deep user intent, a prerequisite for truly personalized suggestions.
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.
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.
