LLM is very good at programming when there are huge number of guardrails against them.
For example, exploit testing is a great usecase because getting a shell is getting a shell.
They kind of acts as a smarter version of infinite monkey that can try and iterate much more efficiently than human does.
On the other hand, in tasks that requires creativity, architecture, and projects without guard rail, they tend to do a terrible job, and often yielding solution that is more convoluted than it needs to be or just plain old incorrect.
I find it is yet another replacement for “pure labor”, where the most unintelligent part of programming, i.e. writing the code, is automated away. While I will still write code from scratch when I am trying to learn, I likely will be able automate some code writing, if I know exactly how to implement it in my head, and I also have access to plenty of testing to gaurentee correctness.
They are also great for programming one off personal projects that frankly, don’t have the use scale that needs rigerous security oversight. Especially since like, if you did it yourself, you probably were not sanitizing the inputs (etc) anyway. You were slapping down some Python code and moving on.
Like, I don’t care if my script to convert Wordpress exports to Markdown files crashes if you feed it a JPEG. I am the only one using it, for this data manipulation task.
People have trouble with the middle ground. AI is useful in coding. It’s not a full replacement. That should be fine, except you’ve got the ai techbros and CEOs on one end thinking it will replace all labor, and the you’ve got the backlash to that on the other end that want to constantly talk about how useless it is.
the times i trust LLMs: when i am using it to look up stuff i have already learned, but i can’t remember and just need to refresh my memory. there’s no point memorizing shit i can look up and am not going to use regularly, and i’m the effective guardrail against the LLMs being wrong when I’m using them.
the times i don’t trust the LLMs: all the other times. if i can’t effectively verify the information myself, why am i going to an unreliable source?
having to explain that nuance over and over, it’s just shorter and easier to say the llm is an unreliable source. which it is. when i’m not doing lazy output, it doesn’t need testing (it still gets at least 2 reviews, but the last time those reviews caught anything was years ago). the llm’s output always needs testing.
LLM is very good at programming when there are huge number of guardrails against them. For example, exploit testing is a great usecase because getting a shell is getting a shell.
They kind of acts as a smarter version of infinite monkey that can try and iterate much more efficiently than human does.
On the other hand, in tasks that requires creativity, architecture, and projects without guard rail, they tend to do a terrible job, and often yielding solution that is more convoluted than it needs to be or just plain old incorrect.
I find it is yet another replacement for “pure labor”, where the most unintelligent part of programming, i.e. writing the code, is automated away. While I will still write code from scratch when I am trying to learn, I likely will be able automate some code writing, if I know exactly how to implement it in my head, and I also have access to plenty of testing to gaurentee correctness.
They are also great for programming one off personal projects that frankly, don’t have the use scale that needs rigerous security oversight. Especially since like, if you did it yourself, you probably were not sanitizing the inputs (etc) anyway. You were slapping down some Python code and moving on.
Like, I don’t care if my script to convert Wordpress exports to Markdown files crashes if you feed it a JPEG. I am the only one using it, for this data manipulation task.
The thing is, you know how it is in your head and you need to lay out that entire context.
And after that you MUST review the code because you’d never know. Wouldn’t call it automation if I have to double check EVERY TIME
People have trouble with the middle ground. AI is useful in coding. It’s not a full replacement. That should be fine, except you’ve got the ai techbros and CEOs on one end thinking it will replace all labor, and the you’ve got the backlash to that on the other end that want to constantly talk about how useless it is.
I’d buy you a beer for that summary. That is exactly SPOT ON.
the times i trust LLMs: when i am using it to look up stuff i have already learned, but i can’t remember and just need to refresh my memory. there’s no point memorizing shit i can look up and am not going to use regularly, and i’m the effective guardrail against the LLMs being wrong when I’m using them.
the times i don’t trust the LLMs: all the other times. if i can’t effectively verify the information myself, why am i going to an unreliable source?
having to explain that nuance over and over, it’s just shorter and easier to say the llm is an unreliable source. which it is. when i’m not doing lazy output, it doesn’t need testing (it still gets at least 2 reviews, but the last time those reviews caught anything was years ago). the llm’s output always needs testing.