When a ‘Boring’ Task Turns Into a 10‑Minute Win With AI
Here is the funny part: I sometimes write about AI, I keep up with almost all the updates from major players like OpenAI and Anthropic, yet yesterday I was complaining about a task that was routine and boring but required a meticulous approach.
Yesterday I remembered that I am surrounded by different models and decided to feed this task to GPT o4-mini-high (perfect for careful work and solid analysis). As a result, a task I would normally spend 1–2 days on was done in 10 minutes.
What I personally miss in current programming tools is this: not just systems that analyze your codebase and generate code, but full-fledged agents that are connected to your database, your message queue server, and, say, Stripe and other APIs I use in my projects. It feels like the arrival of such tools is not far off.
More to explore
AI in Software Development: What Comes Next?
AI. What’s next? Up until around December, using AI in development basically meant: prompt -> copy some code -> paste -> tweak -> repeat. Now this a…
Startup Taxes Between Estonia and Portugal: A Quick Reality Check
As a tax resident of an EU country who files my own returns, today is my quarterly 'Tax Day'. On this day I set aside a few hours to file social security report…
Saylify Update: Fighting Perfectionism, Refactoring, and Finding the Right Focus
I have not written anything about Saylify for a long time, even though I planned to launch in January. Unfortunately, life likes to throw in challenges you can …
Human-Like Memory for LLMs
TL;DR I wrote a manifesto-style essay about a memory model for LLMs that is as close as possible to human memory and lets the system build a relationship histor…