Cloudflare built an oauth provider with Claude
https://github.com/cloudflare/workers-oauth-provider/Open linkView original on lemmy.worldSyndicated from the fediverse. Read and engage on the original instance.
View original on lemmy.worldhttps://github.com/cloudflare/workers-oauth-provider/Open linkView original on lemmy.world
20 replies
Looking through the commit history there are numerous "Manually fixed..." commits, where the LLM doesn't do what the programmer wants after repeated prompting, so they fix it themself.
And here is the problem. It required expert supervision for the prompts to be repeatedly refined, and the code manually fixed, until the code was correct. This doesn't save any labour, it just changes the nature of programming into code review.
If this programmer wasn't already an expert in this problem domain then I have no doubt that this component would be full of bugs and security issues.
So you claim
Agreed, and yet the AI accelerated the project
So they claim.
The fact hat multiple experts reviewed every line of code by hand, I have to say this is impossible unless you’re comparing it to “the junior devs wrote it all and I just kept correcting hem.”
I have to say that you just have to sayed something up
This seems like a perfectly reasonable experiment and not something they’re going to release without extensive human and security review.
Oauth libraries aren’t new and A.I. can probably generate adequate code. My main problem with A.I. for this purpose is that senior developers/experts don’t pop out of thin air. You need junior developers now if you want any real experts in the future. Maybe you need fewer and more specialized training. Maybe the goal is to offload the training cost to Universities and tech companies only want PhDs. Maybe someday LLMs will be good enough to not need much supervision. But that’s not where we are.
We probably need a Level x capability scale like self-driving cars for this sort of thing.
This is true, because AI is not the actual issue. The issue, like with most, is humanity; our perception and trust of AI. Regardless of logic, humanity still chooses illogical decisions.
I think this take undervalues the AI. I think we self select for high quality code and high quality engineers
But many of us would absolutely gawk at something like Dieselgate. That is real code running in production on safety critical machinery.
I'm basically convinced that Claude would have done better
Dieselgate wasn't a "bug" it was an designed in feature to circumvent emissions. Claude absolutely would have done the same, since it's exactly what the designers would have asked it for. Somehow I doubt it would have gone undetected as long if Claude wrote it tho, it'd probably mess it up some other way.
You should look into how Dieselgate worked
I don't think you understand my take
I guess that makes it a bad analogy
Doctors face a similar obstacle before they can practice: medical school and residency. They literally have to jump from zero to hero before the first real paycheck.
Things may evolve this way for senior software developers with a high rate of dropout.
I hear you, and there’s merit to the concerns. My counter is
I don’t know anything about you, obviously, but I suspect you should to take a more nuanced, historical view of Luddites. Writing someone off as a “Luddite” probably isn’t the burn you think it is.
I’m all for technological progress. Who isn’t? It’s the politics and ownership that causes issues.
I apologize back. I didn’t mean to offend. You never know who you’re talking to on a message board and in rereading it, my comment could easily have been taken as hostile. It’s hard to get nuance across in this medium.
Quoting from the repo:
That perfectly mirrors my AI journey. I was very skeptical and my early tests showed shit results. But these days AI can indeed produce working code. But you still need experience to spot errors and to understand how to tell the AI what to fix and how.
Agreed. It creates a new normal for what the engineer needs to actually know. In another comment I claimed that the same was true at the advent of stack overflow
I agree with that. It is a bit like SO on steroids, because you can even skip the copy&paste part. And we've been making fun of people who do that without understand the code for many years. I think with AI this will simply continue. There is the situation of junior devs, which I am kind of worried about. But I think in the end it'll be fine. We've always had a smaller percentage of people who really know stuff and a larger group who just writes code.