I write about AI/ML/System tech reports
Latest from the Blog
Call for Evolocity AI
Carbon or silicon, life thrives on evolution and velocity. We built Evolocity on the belief that both carbon and silicon intelligence must evolve, adapt, and accelerate together in good harmony. Our Mission We’re building a business around helping our enterprise customers succeed with AI. We don’t believe the rest of the world should have to…
Memory-Transformer Research Tree
Carrying on from the last blog: https://shermwong.com/2026/02/22/recsys-for-real-time-ai-agents/ – which is a more high level depiction of possible future states of personalized, real-time AI agents. Here we dig into a deeper topic of how backbone transformer models has evolved so far on memory architectures, which is a key module to enable continuous adaptation of agents. Current…
RecSys for Real-time AI Agents
LLMs need a RecSys layer to truly understand users LLMs are powerful general reasoning engines, but they are not optimized to model long-term user preference evolution. Traditional RecSys systems solved this decades ago by learning persistent user representations from interaction timelines. The key idea is simple: treat a user’s history as a structured signal, not…
