Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I was a top 0.01% Cursor user, then switched to Claude Code 2.0

blog.silennai.com

Post reply on HN
Print view View original

51–60 of 236 posts

Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0

#51

Post by asdff »

lunar_mycroft wrote: post #37
asdff wrote: post #10

>> 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…

For this to work, you'd have to fully specify the behavior of your program in the tests. Put another way, at that point your tests are the program. So the question is, which is a more convenient way to specify the behavior of a program: a traditional programming language, or tests written in that language. I think the answer should be fairly obvious.

Behavior does not need to be fully specified at the outset. It could be evaluated after the run. We've actually done this before in our own technology. We studied birds and their flight characteristics, and took lessons from that for airplane development. What is a bird but the output of a random walk algorithm selected by constraints bound by so many latent factors we might never fully grasp?

Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0

#52

Post by Fire-Dragon-DoL »

asdff wrote: post #10

>> 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…

How do you handle the larger amounts of tests? I did this but my PRs are larger because more tests are needed

Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0

#53

Post by lenerdenator »

asdff wrote: post #10

>> 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…

I can tell you why this won't go this way:

Customers.

When you sell them a technological solution to their problem, they expect it to work. When it doesn't, someone needs to be responsible for it.

Now, maybe I'm wrong, but I don't see any of the current AI leaders being like, "Yeah, you're right, this solution didn't meet your customer's needs, and we'll eat the resulting costs." They didn't get to be "thought leaders" in the current iteration of Silicon Valley by taking responsibility for things that got broken, not at all.

So that means you will need to take responsibility for it, and how can you make that work as a business model? Well, you pay someone - a human - who knows what they're looking at to review at least some of the code that the AI generates.

Will some of that be AI-aided? Of course. Can you make a lot of the guesswork go away by saying "use commonly-accepted design patterns" in your CLAUDE.md? Sure. But you'll still need someone to enforce it and take responsibility at the end of the day if it screws up.

Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0

#54

Post by asdff »

madrox wrote: post #13
asdff wrote: post #10

>> 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

Exactly. As compute increases these algorithms will only get more compelling. You can test and evaluate so many more ideas than any human inventors can generate on their own.

Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0

#55

Post by dns_snek »

asdff wrote: post #10

>> 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…

And how exactly do you foresee probabilistic systems working out in real life? Nobody wants software that seldom does what they expect, and which tends to trend toward desirable behavior over time (where "desirable" behavior is determined by the sum of global feedback and revenue/profit of the company producing it).

Today you send some money to your spouse but it's received by another person with the same name. Tomorrow you order food but your order gets mixed up with someone else's.

Tough luck, the system is probabilistic and you can only hope that the evolutionary pressures influence the behavior to change in desirable ways. This fantasy is a delusion.

Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0

#58

Post by asdff »

asdev wrote: post #35
asdff wrote: post #10

>> 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…

all fun and games until you need to debug the rats nest that you've been continually building. I am actually shocked people who have coded before have been one-shotted into believing this

If a bug rears its head it can be dealt with. Again, this is essentially already practiced by humans through breeding programs. Bugs have come up, such as deleterious traits, and we have either engineered solutions to get around them or worked to purge the alleles behind the traits from populations under study. Nothing is ever bug free. The question is if the bugs are show stoppers or not. And random walk iteration can produce more solutions that might get around those bugs.

Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0

#59

Post by asdff »

bossyTeacher wrote: post #38
asdff wrote: post #10

>> 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…

> ou 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 the code that is used. Humans are expensive but this approach seems incredibly inefficient and expensive. Even a junior can make steady progress against implementing a function, wit…

Today it might not work given what a junior could do against the cost of compute through random walk, but can you say the same in three centuries? We increase compute by the year, but our own brainpower does not increase on those terms. Estimates are that we are actually losing brainpower over time.

Re: I was a top 0.01% Cursor user, then switched to Claude Code 2.0

#60

Post by madrox »

AIorNot wrote: post #31
madrox wrote: post #20

Earlier quoted context omitted.

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.

the (multi) billon dollar question is when that will happen, I think, case in point: the OP is a kid in his 20s describing the history of the last 3 years or so of small scale AI Development ( https://www.linkedin.com/in/silen-naihin/details/experience/ ) How does that compare to those of us with 15-50 years of software engineering experience working on giant codebases that have years of domain rules, customers and u…

As a guy in his mid-forties, I sympathize with that sentiment.

I do think you're missing how this will likely go down in practice, though. Those giant codebases with years of domain rules are all legacy now. The question is how quickly a new AI codebase could catch up to that code base and overtake it, with all the AI-compatibility best practices baked in. Once that happens, there is no value in that legacy code.

Any prognostication is a fool's errand, but I wouldn't go long on those giant codebases.

Post reply on HN