Coding agents have replaced every framework I used • Hacker News Board

Re: Coding agents have replaced every framework I used

#211

Post by woeirua » Sat, Feb 07, 2026, 5:16 PM UTC

jazzyb wrote: post #58

My biggest concern with AI is that I'm not sure how a software engineer can build up this sort of high-level intuition: > I still have to deeply think about every important aspect of what I want to build. The architecture, the trade offs, the product decisions, the edge cases that will bite you at 3am. Without a significant development period of this: > What’s gone is the tearing, exhausting manual labour of typing e…

People said the same thing about the transition to higher levels of abstraction in the past. “How will they write good code if they don’t know assembly? How can they write efficient code if they don’t understand how a microprocessor works?”

These arguments basically just amount to the intellectual equivalent of hazing. 90% of engineers don’t need to know how these things work to be productive. 90% of engineers will never work on a global scale system. Doing very basic things will work for those engineers. Don’t let perfect be the enemy of good enough.

Also, I’d argue that AI will advance enough to capture system design soon too.

Re: Coding agents have replaced every framework I used

#212

Post by eqvinox » Sat, Feb 07, 2026, 5:16 PM UTC

> What’s gone is the tearing, exhausting manual labour of typing every single line of code.

Do I live in a different engineering world? Because that's so much not the exhausting labour part of my work, it's not even the same universe. The exhausting manual labour for me is interacting with others in the project, aligning goals and distributing work, reviewing, testing, even coming up with test concepts, and… actually thinking through what the code conceptually will work like. The most exhausting thing I've done recently is thinking through lock-free/atomic data structures. Ouch, does that shit rack your brain.

Re: Coding agents have replaced every framework I used

#213

Post by hakunin » Sat, Feb 07, 2026, 5:18 PM UTC

exe34 wrote: post #196

hakunin wrote: post #181

Earlier quoted context omitted.

It helps, but it doesn't make it deterministic. LLMs could all be misled together. A different story would be if we had deterministic models, where the exact same input always results in the exact same output. I'm not sure why we don't try this tbh.

it's literally just setting T=0. except they are not as creative then. they don't explore alternative ideas from the mean.

Are you sure that it’s T=0. My comment’s first draft said “it can’t just be setting temp to zero can it?” But I felt like T is not enough. Try running the same prompt in new sessions with T=0, like “write a poem”. Will it produce the same poem each time? (I’m not where I can try it currently).

Re: Coding agents have replaced every framework I used

#214

Post by eqvinox » Sat, Feb 07, 2026, 5:19 PM UTC

geophile wrote: post #178

rglover wrote: post #139

A significant number of developers and businesses are going to have an absolutely brutal rude awakening in the not too distant future. You can build things this way, and they may work for a time, but you don't know what you don't know (and experience teaches you that you only find most stuff by building/struggling; not sipping a soda while the AI blurts out potentially secure/stable code). The hubris around AI is goi…

The article gets at this briefly and moves on: "I can do all of this with the experience on my back of having laid the bricks, spread the mortar, cut and sewn for twenty years. If I don’t like something, I can go in, understand it and fix it as I please, instructing once and for all my setup to do what I want next time." I think this dynamic applies to any use of AI, or indeed, any form of outsourcing. You can outsou…

> any use of AI, or indeed, any form of outsourcing

Oh that's a good analogy/categorization, I hadn't thought about it in those terms yet. AI is just the next cheaper thing down from the current southeast asian sweatshop labor.

(And you generally get what you pay for.)

Re: Coding agents have replaced every framework I used

#215

Post by mark242 » Sat, Feb 07, 2026, 5:19 PM UTC

rglover wrote: post #139

A significant number of developers and businesses are going to have an absolutely brutal rude awakening in the not too distant future. You can build things this way, and they may work for a time, but you don't know what you don't know (and experience teaches you that you only find most stuff by building/struggling; not sipping a soda while the AI blurts out potentially secure/stable code). The hubris around AI is goi…

I would argue that it's going to be the opposite. At re:Invent, one of the popular sessions was in creating a trio of SRE agents, one of which did nothing but read logs and report errors, one of which did analysis of the errors and triaged and proposed fixes, and one to do the work and submit PRs to your repo.

Then, as part of the session, you would artificially introduce a bug into the system, then run into the bug in your browser. You'd see the failure happen in browser, and looking at Cloudwatch logs you'd see the error get logged.

Two minutes later, the SRE agents had the bug fixed and ready to be merged.

"understand how these systems actually function" isn't incompatible with "I didn't write most of this code". Unless you are only ever a single engineer, your career is filled with "I need to debug code I didn't write". What we have seen over the past few months is a gigantic leap in output quality, such that re-prompting happens less and less. Additionally, "after you've written this, document the logic within this markdown file" is extremely useful for your own reference and for future LLM sessions.

AWS is making a huge, huge bet on this being the future of software engineering, and even though they have their weird AWS-ish lock-in for some of the LLM-adjacent practices, it is an extremely compelling vision, and as these nondeterministic tools get more deterministic supporting functions to help their work, the quality is going to approach and probably exceed human coding quality.

Re: Coding agents have replaced every framework I used

#216

Post by redleggedfrog » Sat, Feb 07, 2026, 5:20 PM UTC

verdverm wrote: post #176

otabdeveloper4 wrote: post #168

Earlier quoted context omitted.

Doubt on that. AI usually only wastes time and produces bugs. > bbut you're holding it wrong, just two more prompts and three more agents and it will be a real boy So, you invented an IDE, except more opaque and expensive? Welcome to the club.

You both are likely incorrect, the answer lies in the middle rather than the extremes

This is not just software development wisdom, it's life wisdom.

Re: Coding agents have replaced every framework I used

#217

Post by eqvinox » Sat, Feb 07, 2026, 5:23 PM UTC

kenjackson wrote: post #189

giancarlostoro wrote: post #175

Earlier quoted context omitted.

I find that instructing AI to use frameworks yields better results and sets you up for a better outcome. I use Claude Code with both Django and React which its surprisingly good with. I rather use software thats tried and tested. The only time I let it write its own is when I want ultra minimal CSS.

This. For area where you can use tested and tried libraries (or tools in general) LLMs will generate better code when they use them. In fact, LLMs will be better than humans in learning new frameworks. It could end up being the opposite that frameworks and libraries become more important with LLMs.

> LLMs will be better than humans in learning new frameworks.

I don't see a base for that assumption. They're good at things like Django because there is a metric fuckton of existing open-source code out there that they can be trained on. They're already not great at less popular or even fringe frameworks and programming languages. What makes you think they'll be good at a new thing that there are almost no open resources for yet?

Re: Coding agents have replaced every framework I used

#218

Post by pawelduda » Sat, Feb 07, 2026, 5:23 PM UTC

Nothing fundamentally changed about frameworks. No need to reconsider every single practice because of AI. I think frameworks actually keep agents in check because they're trained on huge set of conventions.

I vibe coded a few of projects in vanilla JS and they eventually became mess, but with a framework they'd at least be structured mess

Re: Coding agents have replaced every framework I used

#219

Post by pphysch » Sat, Feb 07, 2026, 5:24 PM UTC

mark242 wrote: post #215

rglover wrote: post #139

A significant number of developers and businesses are going to have an absolutely brutal rude awakening in the not too distant future. You can build things this way, and they may work for a time, but you don't know what you don't know (and experience teaches you that you only find most stuff by building/struggling; not sipping a soda while the AI blurts out potentially secure/stable code). The hubris around AI is goi…

I would argue that it's going to be the opposite. At re:Invent, one of the popular sessions was in creating a trio of SRE agents, one of which did nothing but read logs and report errors, one of which did analysis of the errors and triaged and proposed fixes, and one to do the work and submit PRs to your repo. Then, as part of the session, you would artificially introduce a bug into the system, then run into the bug…

Automatically solving software application bugs is one thing, recovering stateful business process disasters and data corruption is entirely another thing.

Customer A is in an totally unknown database state due to a vibe-coded bug. Great, the bug is fixed now, but you're still f-ed.

Re: Coding agents have replaced every framework I used

#220

Post by woeirua » Sat, Feb 07, 2026, 5:24 PM UTC

I use coding agents almost exclusively now and I’m going to say yes and no on this one.

Yes, I think there’s the potential to replace some frameworks that abstract away too many details and make things way too complicated for basic apps. A good example of this are ORMs like SqlAlchemy. Every time I use them I think to myself it would be easier to just write SQL myself, but it would be a tremendous amount of boilerplate. Nowadays though it might be worth it for an agent to just write the SQL for you instead!

On the other hand, you have libraries like Django. Sure, an agent _could_ write you your own web server. But wow would it be a waste of tokens and your projects surface area would be dwarfed by the complexity of just building your own alternative to Django. I can’t see that being the right move for years still.