Writing on Andrei Kalamkarov

Using AI every day, and still falling behind

Sat, 03 Oct 2026 00:00:00 +0000

Last week I gave a session on AI development tools to the learning community I run at Concordia University in Montreal. I’ve been using AI tools since April 2022, starting with the GitHub Copilot beta, more than half a year before ChatGPT came out. My team has used them in our daily work for about 2 years. These days I work with Cursor, Claude Code, and Codex, switching depending on the task, the latest features and models, and sometimes my mood.

When AI breaks what it’s trying to fix

Mon, 21 Sep 2026 00:00:00 +0000

Our university CMS turned thirteen in August. It runs on Adobe Experience Manager (AEM), holds about 98,000 live pages, and more than 300 people author content in it. For the past two years, we’ve been using AI to help modernize it. Our current tools include Claude Code, Cursor, and Codex.

The failures I want to talk about came out of that modernization work: changes that looked correct but broke behaviour the system relied on. AI’s advice played a direct role in some of them. Others exposed assumptions a developer could make too. The old behaviour looked like a mistake, but it was a contract, something the system relied on. In a system this old, with this many components and decisions behind it, a lot of the reasoning was never written down, or only partly. Without that context, both people and AI can miss what a seemingly sensible change needs to preserve.

The memory I'm building for AI

Fri, 10 Jul 2026 00:00:00 +0000

AI forgets you between sessions. Start a new session and the model knows nothing about your project, your conventions, or the mistake you told it never to repeat.

You can start from scratch every time, or write it down. A handful of plain-text files hold what the model needs to remember. Without them, your decisions live in your head, every correction is temporary, and the same workflows get re-explained. With them, decisions live beside the work, corrections become rules, and repeatable workflows become reusable instructions.

Knowing when to stop

Fri, 05 Jun 2026 00:00:00 +0000

I was finishing a slide deck, and I went back to the AI for another pass. Then another. The deck already worked. I wasn’t fixing anything, I just wanted to see if one more try would surface a sharper version. None of that is new. What caught me was that I didn’t stop. I used to stop around here, because another pass still took real effort. This time the effort was gone, but the cost of not stopping wasn’t. It had just moved somewhere I couldn’t see.

Sensitive data doesn't mean no AI

Thu, 28 May 2026 00:00:00 +0000

“I can’t use AI. My data is sensitive.”

I hear that often from technical staff at the university where I work.

I manage web and mobile platforms at Concordia University in Montreal. We work across student-facing systems, content workflows, codebases, logs, and integrations where confidential or internal data can appear quickly. So I understand the concern.

And for some data, the concern is the correct answer. There are real consequences when sensitive information crosses a boundary it shouldn’t. Community Bank, a regional US bank, disclosed in 2026 that customer names, Social Security numbers, and dates of birth were exposed through an unauthorized AI application. Vercel investigated unauthorized access to internal systems after a small third-party AI tool’s Google Workspace OAuth app was compromised. Samsung restricted internal use in 2023 after engineers reportedly pasted proprietary code into ChatGPT.

Side quest: bring an old project back to life

Mon, 11 May 2026 00:00:00 +0000

I talk about AI a lot. The most common question I get is some version of “where do I start?” or “what should I build?”

My answer has become simple: pick a side quest. Something small, low-stakes, and actually interesting to you. There are many good side quests. This is one of them: bring an old project back to life.

An old website, a dead blog, a photography portfolio that you let go, or a side project that broke when the servers got upgraded. Pick something you still care about but never quite had the time to fix.

Teaching AI to sound like me

Thu, 23 Apr 2026 00:00:00 +0000

Every time I ask AI to revise my writing, it comes back sounding like AI. It doesn’t just sound less like me, it starts sounding like everyone else’s. The asides (like this one) disappear. My casual phrasing turns polished and forgettable. Then in come the words I’d never write: “delve”, “utilize”, “myriad”.

So I iterate. Re-prompt, paste samples, nudge it closer until it lands. Next session, I’m doing it all over again. The AI had no memory of me.

AI doesn't hallucinate your photos. It edits them.

Tue, 17 Mar 2026 00:00:00 +0000

Every AI model that looks at an image makes editorial decisions: which details matter, which can be smoothed over, whether to add atmosphere or remove clutter. Most people using AI tools encounter these decisions often without noticing. I built Signal Drift to make them visible.

I created it for a university presentation on multi-model AI, using personal photos unlikely to appear in any training set: never shared, several taken the same day. Each model had to work from what it actually saw, not what it had memorized. The same patterns emerged across every subject.

Signal Drift: what happens when four AIs build one app

Tue, 24 Feb 2026 00:00:00 +0000

Every year, Concordia University’s Library hosts Digital Skill-Share Days, a 2-day collaborative learning event where staff and faculty share digital skills with each other. The 2026 edition featured a Lightning Round on Artificial Intelligence and Data on Tuesday, February 24. Four speakers, 5 minutes each to present plus 5 minutes for Q&A, covering everything from the environmental cost of AI to how data work is changing.

I manage web and mobile technology at Concordia, and the title I’d committed to was: “The Multi-Model Approach: Getting Better Answers by Switching Perspectives.” My thesis was straightforward: using multiple AI models intentionally, switching between them based on what each does best, produces better results than sticking with just one. But saying that on a stage doesn’t prove much. I needed to show it with a real project.