Do we really need to qualify our power user level down to 100ppm percentiles...?
I was a top 0.01% Cursor user, then switched to Claude Code 2.0
11–20 of 236 posts
Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0
#12Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0
#13>> You no longer need to review the code. Or instruct the model at the level of files or functions. You can test behaviors instead. I think this is where things will ultimately head. You generate random code, purely random in raw machine readable binary, and simply evaluate a behavior. Most random generated code will not work. some, however, will work. and within that working code, some will be far faster and this is…
You're describing genetic algorithms: https://en.wikipedia.org/wiki/Genetic_algorithm
Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0
#14Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0
#15>> You no longer need to review the code. Or instruct the model at the level of files or functions. You can test behaviors instead. I think this is where things will ultimately head. You generate random code, purely random in raw machine readable binary, and simply evaluate a behavior. Most random generated code will not work. some, however, will work. and within that working code, some will be far faster and this is…
Why should we throw away decades of development in determistic algorithms? Why tech people mentions "geneticists"? I would never select an algorithm with a "good" flying trait for making an airplane works, that's nuts
Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0
#16> my experience from 5 years of coding with AI What AI have you been using for 5 years of coding?
Keyboard autocomplete?
Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0
#17Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0
#18>> You no longer need to review the code. Or instruct the model at the level of files or functions. You can test behaviors instead. I think this is where things will ultimately head. You generate random code, purely random in raw machine readable binary, and simply evaluate a behavior. Most random generated code will not work. some, however, will work. and within that working code, some will be far faster and this is…
Maybe, but you won't be able to test all behaviors and you won't have enough time to try a million alternatives. Just because of the number of possibilities, it'll be faster to just read the code.
Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0
#19I'd love to have you as a top user on autohand [.] ai/cli and interested in your experience with us.
Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0
#20> You no longer need to review the code. Or instruct the model at the level of files or functions. You can test behaviors instead. Maybe for a personal project but this doesn't work in a multi-dev environment with paying customers. In my experience, paying attention to architecture and the code itself results in a much more pliable application that can be evolved.
It's doesn't work...yet. I agree my stomach churns a little at this sentence. However, paying customers care about reliability and performance. Code review helps that today, but it's only a matter of time before it is more performative than useful in serving those goals at the cost of velocity.