I do check most of agent code, not because I really care about every tiny detail but to catch if it's going to shoot itself (and my project) in the foot. If I only check the result and it's OK, it still doesn't mean that in two features I won't totally blow up the app.
I'm a happy little bottleneck, what's wrong with that? How do you even know how to ask it to build stuff for you if you don't understand what foundations are you building on?
Writing commit message (aka. what has changed) gives me a sense of control that I know what's happening and I can confidently build the next thing.
It's amusing to see the stochastic parrot argument in 2026 September. These parrots are extremely good at mimicking a human to the point of getting confusing what thinking even means. At what point we just let it go and accept that sufficiently advanced statistics is just intelligence?
Remember rounded corners? It was a real pain, there were so many hacks to achieve something simple as
border-radius: 16px;
My other favorite was sIFR font loading :) Because font support was... patchy, a technique was invented to replace headers with Flash embeds which rendered the desired font:
...and that was a grand improvement over having to make a "tic-tac-toe" table where you'd be putting things in the particular surrounding cells to fake these fancy border-types.
You create a source of truth which defines all the features and requirements. This can be UI tests, MD files, database, diagrams, whatever that fits your use case.
Which makes you question if this was the plan all along or he was totally naive not to think this though. Imagine if he did this with Aylo (formerly known as MindGeek) :)
I'm a happy little bottleneck, what's wrong with that? How do you even know how to ask it to build stuff for you if you don't understand what foundations are you building on?
Writing commit message (aka. what has changed) gives me a sense of control that I know what's happening and I can confidently build the next thing.
reply