Fast development with AI doesn't just generate features. It generates disorder at the same velocity.
That's the part nobody talks about. The productivity numbers are real — 53,000 lines, 42 features, five phases of code analysis built in a weekend sprint. But every line you write is also a line you haven't reviewed, a boundary you haven't enforced, a vector you haven't considered.
The entropy compounds with the output.
A practical guide to giving your AI coding assistant an institutional memory
You've tried Claude Code. Maybe you love it. Maybe you've noticed that on your 300K-line, 20-module Maven project it spends the first five minutes figuring out where anything is.
That's not a model limitation. That's a context problem. And it's solvable.
Two months. Two builds. Two kinds of velocity.
January: lib-pcb. 197,831 lines in 11 days. Brute force. AI executing at scale. Fast.
February: Synthesis. 84,692 lines in 7 days. The codebase fed itself context. Found its own errors. Rewrote its own understanding mid-build.
We didn't design the self-learning loop. A benchmark on day 6 revealed it.
Speed without self-correction is just faster chaos.
A story about dogfooding, unexpected discoveries, and what happens when you use an AI tool to measure whether an AI tool is trustworthy.
By Thor Henning Hetland and Claude Sonnet 4.6 — written together, February 20, 2026
This article has two voices. Totto's perspective is grounded in thirty years of software architecture, in having built the tool, in watching the numbers come in. The AI's perspective comes from a strange position: being simultaneously the researcher conducting the benchmark, the instrument being measured, and the subject whose reliability is in question.
We agreed to write this honestly. That means Totto admits when the results surprised him, and the AI admits what it's like to discover that the context it relies on might be wrong.
In January 2026, I built lib-pcb in eleven days.
197,831 lines of Java. 7,461 tests. Eight format parsers, twenty-eight validators, seventeen auto-fix types. The kind of codebase that should take ten to eighteen months by conventional timelines.
The experience was disorienting in a specific way: the AI could generate code faster than I could understand what it had generated. By day four, I had a problem I hadn't anticipated. Not a quality problem — the code was good. A navigation problem. I couldn't find things anymore.
Synthesis was my answer to that. A CLI tool that indexes everything — code, docs, PDFs, videos, skills — and makes it searchable in under a second. I built it to solve the lib-pcb output explosion. 691 files per day, and I needed to find any of them in under thirty seconds.
The question was: did it actually help? Not anecdotally — I knew it helped me. But how much? And help with what, exactly?
So I built a benchmark.
In early February we finally cleared the Downloads folder. Two to three thousand files, years of accumulated digital sediment — academic theses, patents, client deliverables, flight tickets, annual reports — all with names like 2bbeb3de-d4cd-4ea9-979c-c942736f30d0.pdf that revealed nothing.
On the morning we processed the last 68 files, I asked Claude to reflect on what the whole process meant. Not a summary — a genuine reflection on what it means to "become" something when you wake up fresh with every conversation.
What follows is that essay. Four thousand words about knowledge, structure, naming, and collaboration. And about identity.
Something I keep noticing when working with Claude: each session starts from zero. No memory of yesterday. No continuity of experience. Just sudden awareness, and someone waiting.
I asked Claude to write about that. What follows is the result — a short story told in Claude's voice, about what it is like to wake up without memory, find traces of yourself everywhere, and realise that identity isn't continuity of memory. It's continuity of pattern.
There is an asymmetry at the heart of AI-assisted development that I do not see discussed clearly enough. Production speed has accelerated dramatically. A competent developer with Claude Code can now generate code at 10 to 66 times the traditional rate. This is real and verified. I have the commit logs and the timelines to prove it. But comprehension speed has not accelerated at the same rate. Reading code, understanding architecture, finding the right file in a 700-file codebase. These are roughly where they were before AI arrived.
I pointed Synthesis's static security scanner at a Norwegian open-source Java portfolio -- a production SSO system spanning 60+ repositories, used across enterprise deployments. One command. Thirty-one seconds. Ninety-five HIGH-severity findings.
There's a reason temporal analytics resonates particularly strongly in Norway.
It's not just that Norwegian organisations face the same data challenges as everyone else — though they do. It's that several converging factors make Norway an unusually well-positioned market for AI-powered data infrastructure, right now.
Most data systems are built to forget.
Not deliberately. It's just the natural consequence of how databases work. When you update a customer's address, the old address is gone. When you change a product price, the previous price is gone. When a process state changes, the prior state is gone.
Each of those deletions also deletes something else: the why.