Basically all our code gets written by agents now, and so do the tests. Usually same session, same model. And I keep hitting the same loop:

1. Agent builds the feature

2. Agent writes the tests, everything green

3. Ship it

4. A user hits an edge, I dig in, and the tests were checking what the code does, not what the ticket asked for. Suite was green the whole time.

The annoying part is that if the model misread the ticket, its tests misread it the same way. It's basically marking its own homework. The model is just agreeing with itself.

I came up with this concept after I failed to set New Year s resolutions at the beginning of 2023 and was disappointed that I didn t achieve much.

Since 2024, I ve been practising quarterly goal-setting.

I see this pattern all the time with creators and small teams (and lived it myself):

You start with Google Docs + Google Sheets because:

• they re free

• everyone knows how to use them

• we ll switch later when it gets serious

Fast forward a few months and suddenly you have:

I don t mean this in a disrespectful way or anything like that, but throughout my life, I ve come across (and I m sure you have too) several products whose actual usefulness wasn t exactly impressive, but their creators still made a huge amount of money.

For me, for example, it was:

• Fidget spinners (2017). At the peak, the global market was estimated at hundreds of millions to over $1 billion.

• Metaverse land (2021) valuation could be for tens or even hundreds of thousands of dollars each, with the overall market reaching hundreds of millions during the peak hype cycle. I bought one too. :D (actually was scammed).

• Pet Rock (1975) the creator became a millionaire within a few months.

I recently installed @Augment Code based on an ad somewhere, and I'm super impressed, but haven't heard a peep about it in most channels. But it got me wondering what else I'm missing. This is a crowded field with a few frontrunners and a lot of more esoteric newcomers, but I want to know about the ones that blow your mind but hardly get any coverage.

Yesterday, I came across an article on TechCrunch that OpenAI is upgrading ChatGPT search with shopping features.

Slowly but surely, ChatGPT is taking over Google's role and doing it well. I ve noticed it myself, especially how it s replaced much of my browsing.

Everyone talks about automating the FANCY stuff, but the thing that actually gave me hours back was automating my weekly metrics screenshot for investors. Ten minutes every Monday, gone forever, took me a year to bother setting it up.

Not looking for tool promos, more curious about the task itself. What was your "why did I do this manually for so long" moment?