I Can Generate Faster Than I Can Think: Tokenmaxxing, verification hell, and the creativity trap of infinite AI
16 min read👏 7
- tokenmaxxing
- agentic coding
I used to think the bottleneck was execution.
02 / Notes
Blog
Essays, notes, and build logs on design systems, AI interfaces, and shipping polished web products.
From Smallville to MemoryArena: How Far Has Agent Memory Come?
10 min read- agent memory
- llm
In 2023, almost everyone thought agent memory was mostly a context-window problem.
It took me three months to “vibe code” a simple Pomodoro app
4 min read👏 17- vibe coding
- pomodoro technique
My mentor survived three part-time jobs and bone-deep poverty with a simple tool: the Pomodoro technique. It worked for him. And for years, it has worked…
We Built Oracles. We Need Librarians — Why the “R” in RAG Is Harder Than Google Search
6 min read👏 1- rags
- agent memory
- llm
Search has been with us since the Yahoo! days, and for most people it feels “solved.” You type a few words, hit enter, and out comes a list that’s “good…
Emergence AI Broke the Agent Memory Benchmark. I Tried to Break Their Code.
11 min read👏 24- llm
- rags
- agent memory
I’ve talked a lot about the LongMemEval dataset on my blog. If you’re not deep in the agent memory space, you’ve probably never heard of it. It’s a poster…
SLMs as the New Memory Core: A Deep Dive into Conversational Understanding
8 min read👏 13- agent memory
- llm
- lms
If you’ve been keeping an eye on AI lately, you’ve probably noticed a big shift. Models have moved beyond just answering questions or generating clever…
Stop Pretending Your Agent Memory Isn’t RAG
10 min read👏 21- llm
- rags
- agent memory
Note: This article was updated on September 2, 2025, to incorporate clarifications from Sarah, the founder of Letta. The original version categorized…
From Beta to Battle‑Tested: Picking Between Letta, Mem0 & Zep for AI Memory
7 min read👏 82- ai memory
- llm agent
- rags
The revolution in Large Language Models (LLMs) is undeniable, but their stateless nature remains a significant hurdle. Like Dory from Finding Nemo, they…
The AI Memory Challenge, Part 1: We Asked Mem0 to Remember Five Things. Here’s How It Did.
15 min read👏 73- cognition
- llm agent
- memories
- ai
You’ve seen the hype: GPT-4o hits 128k tokens! Claude 3 digests novels! Sounds like AI memory’s cracked, time to pack up?
Prompting Smarter with Chain of Draft (CoD): Hype vs. Reality
7 min read👏 10- llm
- prompt engineering
A couple of days ago, YouTube shoved this video in my face:
Setting up Letta (MemGPT) with Supabase
9 min read👏 13- ai
- llm
- agents
If you’ve been building AI applications, you’ve probably noticed something frustrating — LLMs have terrible memory. Sure, ChatGPT and Claude seem to…
