Burak Avar

We use AI to improve something in the process (mostly to speed up the process).

But whenever I see and suspect that something is generated by LLMs, I feel that the person on the other side has slopped it a bit (and subconsciously I perceive it as "something less").

I keep running into this while building.

There s always another feature that sounds useful on its own.

Another setting.
Another metric.
Another automation.
Another smart layer.

But at some point, the product starts asking the user to understand the system instead of the system understanding the user.

After 3 months of solo building on evenings/weekends, I noticed my 7 9pm block is where ~80% of shipped code lives. Everything else mornings, lunch breaks, weekend afternoons turns into planning, browsing, or half-baked drafts that get thrown out.

Two things I had to change to protect that window: killing all notifications until 9pm, and doing planning the night before so I don't waste the shipping hours on "what should I build today."