Becoming an AI-Native Engineer
rfitz.io
Becoming an AI-Native Engineer
1–10 of 30 posts
Re: Becoming an AI-Native Engineer
#2it’s really hard to be consistently “excited” about this space when half of the AI companies are proudly proclaiming their commitment to try and automate your job (doubtful but the mantra is suffocating) and the other half are just about increasing your productivity (you get more done at the same pay). i guess some boilerplate is truly automated which is a mild qol improvement
Re: Becoming an AI-Native Engineer
#3The more I use LLMs to code, the farther I stray from the joy of coding.
I won't regurgitate the common sentiment of it being like pair programming with an oddly spiky profile junior engineer savant. I find my emotions being activated too often in having to recontextualize or reign in or re-orient or repeat.
If I wrote code that doesn't work, that is on me. If I have to read code that doesn't work, I didn't write it, and it's veracity or accuracy are only uncoverable by me - but are already being treated as gospel by my AI peer, and the LLM keeps asserting issues with "my" code that I don't yet feel I have ownership over because I have not ingested it fully is supremely tiring. The whiplash feels almost like an abusive relationship.
I want to get back to feeling accomplished once finished with a coding session, not like I just went through a kafkaesque ringer.
Re: Becoming an AI-Native Engineer
#4I don't really disagree with anything in this post, but the advice is so basic it could have easily been written by an LLM, and apologies for my jadedness but I've seen like a million other posts with the same advice. The advice is simply:
1. Write detailed prompts.
2. Don't trust generated code output - it must be thoroughly reviewed, and feedback should be given back to the LLM.
3. AIs are very helpful for those learning new architectural patterns.
4. Try different tools.
If you really want to learn about using AI to write code (including the pros and cons), I think this post, https://news.ycombinator.com/item?id=44159166, is excellent. Note the author of the Cloudflare OAuth component, kentonv, makes a lot of good, insightful comments in that thread IMO.
Re: Becoming an AI-Native Engineer
#5The more I use LLMs to code, the farther I stray from the joy of coding. I won't regurgitate the common sentiment of it being like pair programming with an oddly spiky profile junior engineer savant. I find my emotions being activated too often in having to recontextualize or reign in or re-orient or repeat. If I wrote code that doesn't work, that is on me. If I have to read code that doesn't work, I didn't write it,…
> The more I use LLMs to code, the farther I stray from the joy of coding.
I agree. The way I put it is that it feels like programming has been turned into the job of an editor, when it used to be an author. Of course, editing was always a huge part of programming, probably the biggest part, but I always kinda felt like reviewing and editing was more the "brussel sprouts" part of the job and authoring the "ice cream". I was fine to eat my brussel sprouts if I got to have some scoops of ice cream sprinkled throughout, but now it feels like just endless plates of brussel sprouts.
Re: Becoming an AI-Native Engineer
#6it’s really hard to be consistently “excited” about this space when half of the AI companies are proudly proclaiming their commitment to try and automate your job (doubtful but the mantra is suffocating) and the other half are just about increasing your productivity (you get more done at the same pay). i guess some boilerplate is truly automated which is a mild qol improvement
Often in the past I have felt that software engineering contains a lot of reinventing the wheel again and again in slightly different ways. In an organisation that wants to achieve anything you're often stuck collectively fantasising about all the things you could do "if only" A, B, C and D were solved problems within the internal IT landscape. My hope is that the increased productivity can eventually translate into actually doing those things.
We fret about AI adding a bunch of bad code but I see that there are clear methods for avoiding/mitigating this. (Just make sure to test and otherwise verify that the code does the right thing. Make it transparent and easy to replace etc etc.)
Sure it can be used to add a bunch of technical debt but wielded right it can just add well be used to cut down the debt.
Re: Becoming an AI-Native Engineer
#7The more I use LLMs to code, the farther I stray from the joy of coding. I won't regurgitate the common sentiment of it being like pair programming with an oddly spiky profile junior engineer savant. I find my emotions being activated too often in having to recontextualize or reign in or re-orient or repeat. If I wrote code that doesn't work, that is on me. If I have to read code that doesn't work, I didn't write it,…
> The more I use LLMs to code, the farther I stray from the joy of coding. I agree. The way I put it is that it feels like programming has been turned into the job of an editor, when it used to be an author. Of course, editing was always a huge part of programming, probably the biggest part, but I always kinda felt like reviewing and editing was more the "brussel sprouts" part of the job and authoring the "ice cream"…
You can call it editor or you can call it director/architect. Instead of tapping out characters you spend more time making interesting and more high level decisions.
Re: Becoming an AI-Native Engineer
#8it’s really hard to be consistently “excited” about this space when half of the AI companies are proudly proclaiming their commitment to try and automate your job (doubtful but the mantra is suffocating) and the other half are just about increasing your productivity (you get more done at the same pay). i guess some boilerplate is truly automated which is a mild qol improvement
I find it helpful to ignore the hype and the pitches, and instead focus on how AI tools are enabling better software to be made. I may personally prefer old workflows, but if they are inefficient and I cling to them, then my value as a software professional will trend to zero over time. On the other hand, the volume of software and it's importance is still continuing to increase—AI is only accelerating this trend. So understanding how software works and what AI can and can't do with it has never been of higher value.
Sure investors and CEOs want to reduce software engineering costs, but at the end of the day software is built to serve human needs, and only humans can reason and make a judgement call about whether software systems are working well or not, and because software is so precise and deterministic, there will always need to be someone who thinks like a programmer to tell the AI what to do with sufficient precision to be useful. Sure I can imagine AGI could at some point invalidate that thinking, but I believe we are very far from that point if its even possible, and even if we do reach that point we'll need massive social change or the pitchforks will be coming out from many directions.
Re: Becoming an AI-Native Engineer
#9The more I use LLMs to code, the farther I stray from the joy of coding. I won't regurgitate the common sentiment of it being like pair programming with an oddly spiky profile junior engineer savant. I find my emotions being activated too often in having to recontextualize or reign in or re-orient or repeat. If I wrote code that doesn't work, that is on me. If I have to read code that doesn't work, I didn't write it,…
> The more I use LLMs to code, the farther I stray from the joy of coding. I agree. The way I put it is that it feels like programming has been turned into the job of an editor, when it used to be an author. Of course, editing was always a huge part of programming, probably the biggest part, but I always kinda felt like reviewing and editing was more the "brussel sprouts" part of the job and authoring the "ice cream"…
I've been struggling with the same thing. It's the same reason I didn't really want to go on the management path because it loses the authoring part. But now it seems to be forced on us.
That being said, there are lots of brussel sprouts in authoring sometimes - the boilerplate and wrote stuff we've done a billion times. You can make Claude eat those brussel sprouts which is nice.
also, very nice analogy, but don't besmirch the good brussel sprout name. I think in real life, cooked properly, I might even prefer them to ice cream.
Re: Becoming an AI-Native Engineer
#10Earlier quoted context omitted.
> The more I use LLMs to code, the farther I stray from the joy of coding. I agree. The way I put it is that it feels like programming has been turned into the job of an editor, when it used to be an author. Of course, editing was always a huge part of programming, probably the biggest part, but I always kinda felt like reviewing and editing was more the "brussel sprouts" part of the job and authoring the "ice cream"…
You can call it editor or you can call it director/architect. Instead of tapping out characters you spend more time making interesting and more high level decisions.
I totally disagree with this, and that's because (like this blog post says) the output can't be trusted - you still need to review every line of generated code. The recent post I linked in another comment about the Cloudflare OAuth implementation had a catastrophic bug that would have been "game over" if the engineer wasn't such an expert in the field.
So it's like an architect but only if you need to triple check every nail, bolt and screw because otherwise the building will probably collapse.