I find chat for search is really helpful (as the article states)
You can give them more latitude for things you know how to check.
I didn't know how to setup the right gnarly typescript generic type to solve my problem but I could easily verify it's correct.
More specifically, I didn't know how to solve it, though obviously could have spent much more time and learned. There were only a small number of possible cases, but I needed certain ones to work and others not to. I was easily able to create the examples but not find the solution. With looping through claude I could solve it in a few minutes. I then got an explanation, could read the right relevant docs and feel satisfied that not only did everything pass the automated checks but my own reasoning.
If you are lucky to have the LLM fix it for you, great. If you don't know how to fix it yourself and the LLM doesn't either, you've just wasted a lot of time.
> If you merely know how to check, would you also know how to fix it after you find that it's wrong?
Probably? I'm capable of reading documentation, learning and asking others.
> If you don't know how to fix it yourself and the LLM doesn't either, you've just wasted a lot of time.
You may be surprised by how little time, but regardless it would have taken more time to hit that point without the tool.
Also sometimes things don't work out, that's OK. As long as overall it improves work, that's all we need.
I use chat for things I don't know how to do all the time. I might not know how to do it, but I sure know how to test that what I'm being told is correct. And as long as it's not, I iterate with the chat bot.
I suppose we could ask the question: Are LLMs better at writing secure code than humans? I'll admit I don't know the answer to that, but given what we know so far, I seriously doubt it.
The issue is, there are always subtle aspects to problems that most developers only know by instinct. Like, "how is it doing the unicode conversion here" or "what about the case when the buffer is exactly the same size as the message, is there room for the terminating character?". You need the instincts for these to properly construct tests and review the code it did. If you do have those instincts, I argue you could write the code, it's just a lot of effort. But if you don't, I will argue you can't test it either and can't use LLMs to produce (at least) professional level code.
This means, it's okay to use LLM to try something new that you're on the fence about. Learn it and then once you've learned that concept or the idea, you can go ahead to use same code if it's good enough.
(Which goes for StackOverflow, etc.)
I'm still learning where it's usable and where I'm over-reaching. At present I'm at about break-even on time spent, which bodes well for the next few years as they iron out some of the more obvious issues.
But "writing a wrapper" is (presumably) a process you're familiar with, you can tell if it's going off the rails.
What's way more likely to know the best practices is the documentation. A few months ago there was a post that made the rounds about how the Arc browser introduced a really severe security flaw by misconfiguring their Firebase ACLs despite the fact that the correct way to configure them is outlined in the docs.
This to me is the sort of thing (although maybe not necessarily in this case) out of LLM programming. 90% isn't good enough, it's the same as Stackoverflow pasting. If you're a serious engineer and you are unsure about something, it is your task to go to the reference material, or you're at some point introducing bugs like this.
In our profession it's not just crypto libraries, one misconfigured line in a yaml file can mean causing millions of dollars of damage or leaking people's most private information. That can't be tackled with a black box chatbot that may or may not be accurate.
you're equating "unfamliar" with "don't know how to do" but I will claim you do know how to do it, you would just be slow because you have to reference documentation and learn which functions do what.
Learning how something works is critical or it's far worse than technical debt.
Having an LLM do something for you that you don't know how to do is asking for trouble. An expert likely can off load a few things they aren't all that important, but any junior is going to dig themselves into a significant hole with this technique.
But asking an LLM to help you learn how to do something is often an option. Can't one just learn it using other resources? Of course. LLMs shouldn't be a must have. If at any point you have to depend upon the LLM, that is a red flag. It should be a possible tool, used when it saves time, but swapped for other options when they make sense.
For an example, I had a library I was new to and asked copilot how to do some specific task. It gave me the options. I used this output to go to google and find the matching documentation and gave it a read. I then when back to copilot and wrote up my understanding of what the documentation said and checked to see if copilot had anything to add.
Could I have just read the entire documentation? That is an option, but one that costs more time to give deeper expertise. Sometimes that is the option to go with, but in this case having a more shallow knowledge to get a proof of concept thrown together fit my situation better.
Anyone just copying an AI's output and putting it in a PR without understanding what it does? That's asking for trouble and it will come back to bite them.
Indeed getting good at writing code using LLMs demands being very good at reading code.
To that extent its more like blitz chess than autocomplete. You need to think and verify in trees as it goes.
Not really. I often use Chat to understand codebases. Instead trying to navigate mature, large-ish FOSS projects (like say, the Android Run Time) by looking at it file by file, method by method, field by field (all to laborious), I just ask ... Copilot. It is way, way faster than I and are mostly directionally correct with its answers.