TBH Claude Code max pro's performance on coding has been abhorrent(bad at best). The core of the issue is that the plan produced will more often than not use humans as verifiers(correctness, optimality and quality control). This is a fundamentally bad way to build systems that need to figure out if their plan will work correctly, because an AI system needs to test many plans quickly in a principled manner(it should be optimal and cost efficient).
So you might get that initial MvP out the door quickly, but when the complexity grows even just a little bit, you will be forced to stop and look at the plan and try to get it to develop it saying things like: "use Design agent to ultrathink about the dependencies of the current code change on other APIs and use TDD agent to make sure tests are correct in accordance with the requirements I stated" and then one finds that even the all the thinking there are bugs that you will have to fix.
Source: I just tried max pro on two client python projects and it was horrible after week 2.
How much of the product were you able to build to say it was good/reliable? IME, 70 hours can get you to a PoC that "works", building beyond the initial set of features — like say a first draft of all the APIs — does it do well once you start layering features?
It depends on how you use it. The "vibe-coding" approach where you give the agen naive propmts like "make new endpoint" often don't work and fail.
When you break the problem of "create new endpoint" down into its sub-components (Which you can do with the agent) and then work on one part at a time, with a new session for each part, you generally do have more success.
The more boilerplate-y the part is, the better it is. I have not really found one model that can yet reliably one-shot things in real life projects, but they do get quie close.
For many tasks, the models are slower than what I am, but IMO at this point they are helpful and definitely should be part of the toolset involved.
> The more boilerplate-y the part is, the better it is. I have not really found one model that can yet reliably one-shot things in real life projects, but they do get quie close.
This definitely feels right from my experience. Small tasks that are present in the training data = good output with little effort.
Infra tasks (something that isn't in the training data as often) = sad times and lots of spelunking (to be fair Gemini has done a good job for me eventually, even though it told me to nuke my database (which sadly, was a good solution)).
Posting here from an anonymized account about Meta. No one probably recalls that meta stopped most of their background location services(Remember Nearby Friends) on the main application ~2021-2022[1]. It was just not even worth a repeat NYT story with this much money on infra to collect locations.
But, this is basically after they figured how to do "good enough" location targetting using IP and a bunch of this info this guy talked about. You don't actually need a lat, long, just the 1 mile radius/city area is good enough to run ads and they have ALL of that.
This was why meta's revenue dropped so much after apple's move, they could not fall back to collecting precise location. This is the last game in town. You shut this down, meta's precise targetting will suffer gravely, ads will become flakey.
One last thing. You may ask, who are the businesses that need precise lat longs? are like this one[2]. These businesses are like whack-a-mole. They saturate the app market steal data get money and shit down when someone yells and in a few months and comeback again, rebranded and come back as another app. They exist not just to collect data but to act as an arbiter on who get eyeballs on IRL activities to influence behavior at the (Top of the funnel) TOFu. In the Worst. Possible. Way.
So you might get that initial MvP out the door quickly, but when the complexity grows even just a little bit, you will be forced to stop and look at the plan and try to get it to develop it saying things like: "use Design agent to ultrathink about the dependencies of the current code change on other APIs and use TDD agent to make sure tests are correct in accordance with the requirements I stated" and then one finds that even the all the thinking there are bugs that you will have to fix.
Source: I just tried max pro on two client python projects and it was horrible after week 2.