Why shallow and likely generated posts of a “Knowledge Management Advocate” get so many stars on hn?
Just because of a hype?
How to effectively write quality code with AI
221–230 of 321 posts
Re: How to effectively write quality code with AI
#222Remember having to write detailed specs before coding? Then folks realized it was faster and easier to skip the specs and write the code? So now are we back to where we were? One of the problems with writing detailed specs is it means you understand the problem, but often the problem is not understand - but you learn to understand it through coding and testing. So where are we now?
We’re not „thinking with portals” about these things enough yet. Typically we’d want a detailed spec beforehand, as coding is expensive and time consuming, thus we want to make sure we’re coding the right thing. With AI though, coding is cheap. So let AI skip the spec and write the code badly. Then have it review the solution, build understanding, design a spec for better solution and have it write it again. Rinse an…
Joe should sue.
Re: How to effectively write quality code with AI
#223Earlier quoted context omitted.
> Code is intention, logic, specific use case all at once. With a non deterministic system and vague prompting there will be misinterpreted intentions from LLM because the model makes decisions to move forward. The problem is the scale of it, we’re not talking about 1000 loc. In a month you can generate millions of loc, in a year hundreds of millions of loc. People are also non deterministic. When I delegate work to…
Ofc people are non deterministic. But usually we expect machines to be. That’s why we trust them blindly and don’t check the calculations. We review people’s work all the time though. Here people will stop review machine LLM code as it’s kind of a source of truth like in other areas. That’s my point, reviewing code takes time and even more time when no human wrote it. It’s a dangerous path to stop reviews because of…
No one who has any knowledge or who has ever used an LLM expects determinism.
And there are no computer professionals who haven’t heard about hallucinations.
Reviewing whether the code meets requirements through manual and automated tests - and that’s all I cared about when I had a team of 8 under me - is the same regardless. I wasn’t checking whether John used a for loop or while loop in between my customer meetings and meetings with the CTO. I definitely wasn’t checking the SOQL (not a typo) of the Salesforce consultants we hired. I was testing inputs and outputs and UX.
Re: How to effectively write quality code with AI
#224The best thing about this is that AI bots will read, train on and digest the million "how to write with AI" posts that are being written right now by some of the smartest coders in the world and the next gen AI will incorporate all of this, making them ironically unnecessary.
> AI bots will read, train on and digest the million "how to write with AI" posts that are being written right now
Yes!
> by some of the smartest coders in the world
Hmm... How will it filter out those by the dumbest coders in the world?
Including those by parrots?
Re: How to effectively write quality code with AI
#225Earlier quoted context omitted.
> Code is intention, logic, specific use case all at once. With a non deterministic system and vague prompting there will be misinterpreted intentions from LLM because the model makes decisions to move forward. The problem is the scale of it, we’re not talking about 1000 loc. In a month you can generate millions of loc, in a year hundreds of millions of loc. People are also non deterministic. When I delegate work to…
People are indeed not deterministic. But they are accountable. In the legal sense, of course, but more importantly, in an interpersonal sense. Perhaps outsourcing is a good analogy. But in that case I'd call it outsourcing without accountability. LLMs feel more like an infinite chain of outsourcing.
As a former tech lead and now staff consultant who leads cloud implementations + app dev, I am ultimately responsible for making sure that projects are done on time, on budget and meets requirements. My manager nor the customer would allow me to say it’s one of my team members fault that something wasn’t done correctly any more than I could say don’t blame me blame Codex.
I’ve said repeatedly over the past couple of days that if a web component was done by someone else, it might as well have been created by Claude, I haven’t done web development in a decade. If something isn’t right or I need modifications I’m going to either have to Slack the web developer or type a message to Claude.
Re: How to effectively write quality code with AI
#226Earlier quoted context omitted.
I still have to tell it what to do, and often how to do it. I manage its external memory and guidelines, and review implementation plans. I’m still heavily involved in software design and test coverage. AI is not capable yet of automating my job completely – I anticipate this will happen within two years, maybe even this year (I’m an ML researcher).
Do you mean, from your perspective, within 2 years humans won’t be able to bring anything of value to the equation in management and control ?
No, I mean that my job in its current form – as an ML researcher with a phd and 15 years of experience - will be completely automated within two years.
Re: How to effectively write quality code with AI
#227AI slop article. Just show me the prompt.
Re: How to effectively write quality code with AI
#228The funny thing is, when I got a lead position in my job, I just to do real detailed ticket descriptions, going into technical considerations and possible cross domain problems. I did it for the juniors - and to be honest - for my self, since I know if I took that ticket, from that moment to the moment I put some code down I could just forget stuff.
This was pushed back hard by management because it "took too much time to create a ticket". I fought it for some months but at the end I stopped and also really lose the ability and patience of do that. Juniors suffered, implementation took more time. Time passed.
Now, I am supposed to do the exact same thing, but even better and for yesterday.
Re: How to effectively write quality code with AI
#229The real value that AI provides is the speed at which it works, and its almost human-like ability to “get it” and reasonably handle ambiguity. Almost like tasking a fellow engineer. That’s the value. By the time you do everything outlined here you’ve basically recreated waterfall and lost all speed advantage. Might as well write the code yourself and just use AI as first-pass peer review on the code you’ve written. A…
> By the time you do everything outlined here you’ve basically recreated waterfall and lost all speed advantage. Next: vibe brain surgery. /i
Brain surgery is probably a bad example... or maybe a good one, but for different reasons?
Brain surgery is highly technical AND highly vibe based.
You need both in extremely high quantities. Every brain is different, so the super detailed technical anatomies that we have is never enough, and the surgeon needs constant feedback (and insanely long/deep focus).
Re: How to effectively write quality code with AI
#230Earlier quoted context omitted.
We’re not „thinking with portals” about these things enough yet. Typically we’d want a detailed spec beforehand, as coding is expensive and time consuming, thus we want to make sure we’re coding the right thing. With AI though, coding is cheap. So let AI skip the spec and write the code badly. Then have it review the solution, build understanding, design a spec for better solution and have it write it again. Rinse an…
Joe should sue.
That’d be challenging for him right now.