Writing from Sebastian Lund about LLMs in production, memory systems, agents, evals, and AI infrastructure.
I was hired to lead the AI rollout for 900+ engineers at a $2bn+ sports betting company. Sports betting is an older industry, and older industries tend to have a larger gap to close when technology moves quickly. You cannot drag everyone across that gap yourself. The only way to push AI adoption at that scale is to create internal sustained motion inside the company so people can keep moving…
A good career can quietly turn into a hamster wheel that drains you. You work on a hard, ambiguous problem, solve it, people praise the solving, and you pick up a bigger problem within the same domain. People start to expect you to work on that type of problem. Your salary increases over time, scope grows indefinitely. It turns into a wheel. Being part of this wheel is hard to notice because it…
Every developer shipping AI right now has the same complaint: the developer experience is broken. Tutorials are out of date. Libraries have gotchas. Frameworks leak. “Solutions” need 3+ hacks to fit. Every deployment is bespoke. The primitives underneath AI engineering refuse to hold still. Model APIs, context windows, tool-calling conventions, agent frameworks, “best practices”: every layer…
A founder friend messaged me recently: When do we trigger compaction? Context is finite, so at some point we have to compress. Priority-based, task-specific, time-based… what have you tried? These are the questions most people start with. How do I compress? When do I trigger that? How do I retrieve what’s relevant? They’re the right questions, but going from concepts to a working implementation…
Most LLM memory systems make your product worse. Engineers add them expecting a database. Instead they get something slow, expensive, and unreliable. Mention memory tools to anyone running agents in production and you get the same reaction: “It’s heavy.” “The latency kills us.” “Great in theory.” The problem isn’t the tools. It’s that there is no universal LLM memory . The industry uses several…
Thursday afternoon. Your security team pings you: Jon @blue-team: The Next.js RCE vulnerability just dropped. What version were we running on Monday? Were we exposed? Do we need to check logs for exploitation attempts? You: Wait what? What versions are affected? Jon @blue-team: 15.0.5, 15.1.9, 15.2.6, 15.3.6, 15.4.8, 15.5.7, 15.6.0-canary.58, 16.0.7 have been patched and are safe. You ask your…
Over the last few weeks, I’ve been digging deep into LLM memory systems. My last post described the techniques they use. Whenever I mentioned tools like Mem0 to engineers running agents in production, I got the same reaction: a collective sigh . “It’s heavy.” “The latency kills us.” “Great in theory.” I wanted to understand why. Systems like Mem0 & Zep are sold on the promise of reducing cost by…
LLMs don’t have memory. They’re stateless: each response requires resending the entire conversation history. Yet they reference earlier messages and maintain context across long interactions. How? LLMs do not remember anything LLMs are stateless. Each inference is independent. Generating a single output token requires processing all preceding tokens as input. To answer coherently the LLM needs…
Every team building LLM apps hits the same wall: users expect full message history, but LLMs have hard context limits. The Problem Users often need to review and trust the full conversation history. LLMs need compaction to meet latency and token budgets. Those two requirements pull in opposite directions. So we built context-store to improve LLM latency while preserving full history for your…