Every 3 lines coming out of Claude has got a bug in it.
There is going to be a lot of demand for people to clean it up.
LLMs are eroding my software engineering career and I don't know what to do
571–580 of 1001 posts
Re: LLMs are eroding my software engineering career and I don't know what to do
#572Earlier quoted context omitted.
> It's the expertise of engineers on the team that push it back on track. But how are you so sure your colleagues are not more "expert" than you? Prior LLMs there was room for very good engineers and mediocre engineers to work together in 99% of the companies out there. With LLMs, only the "best" engineers will survive, because nobody needs mediocre engineers anymore. This being HN, I imagine every engineer reading t…
> With LLMs, only the "best" engineers will survive, because nobody needs mediocre engineers anymore. LLMs are going to show that there's a huge divide in "engineers" between people who love "coding" and people who like "engineering". The group of people kicking and screaming the most are the people who love code and don't want to see their coding go away. These are typically the build vs buy folks. "We can't use any…
Very well said and if you look at some of the other threads on hacker news about why people don’t like AI it specifically because they like typing and coding
The majority of my time is an engineering manager has been teaching “engineers” how to actually do engineering with any kind of rigor
The number of engineers who have an absolutely no theoretical structural or system basis for what they’re doing is the vast vast majority
Re: LLMs are eroding my software engineering career and I don't know what to do
#573It's odd to me how quickly the author devalues their own experience just because AI can do certain things well. There's a huge chasm between what AI can do when prompted by an expert software engineer vs a non-technical person. Sure the models and the tooling will get better, but it still needs to be driven by someone with an intuition for how software works and able to dig in when necessary to unpack and correct the…
I agree here. Sure, certain tasks that would take weeks are just one prompt away now. But out of a group of 100 people, how many are able to come up with the correct prompt?
Re: LLMs are eroding my software engineering career and I don't know what to do
#574My career path is suprisingly similar to the author's. Weirdly enough, what he takes as the first pillar to fall is the one I see most undamaged currently. LLMs routinely fail at our business specifics: Local tax regulations, particularities of the accounting process, specifics of our ledger implementations. They're great at refactoring, translating between languages, tracing bugs on existing code even, but there is…
This. Once you're building something that genuinely hasn't been built before, LLMs cannot be trusted with any architectural decisions. I'm building a product based around various physics simulations, so it's purely first principles, but without active research, thinking, and challenging, it produces computational code literally hundreds of orders of magnitude slower WHILE implementing absurd fallbacks and shortcuts t…
I find that too, Claude Code is constantly trying to break the architecture patterns and do hacky stuff
Like its only focused on solving the local problem as easy as possible
Re: LLMs are eroding my software engineering career and I don't know what to do
#575Wut? I pilot LLMs all day but there's no way in hell I'd agree to be at the helm of a finance product. That first pillar is still there. Maybe the author isn't aware of the impact they have, but I know, with the evidence of reverted PRs, that when I step outside my area of deep knowledge I can no longer call BS on the agents. Our most capable agent, with access to the same kind of distributed systems the author talks…
In software dev, for a big finance corp
I like your comment, want to try to expand on it
Comment long but there is a TL;DR at the bottom
My theory is that there are 4 areas to domain knowledge worth taking about here - there may be more but I like 2*2 matrices
1) explicit internal requirements - core of how the how the app should work towards achieving your business objectives - code expresses what should be done and to a pretty large extent, why it should be done - from business unit requirements - we are building a tool to do “X”
2) implicit internal requirements - core of how the how the app should work towards achieving your business parameters and constraints
eg profit = selling price - ( total of costs )
- code expresses what should be done but really can’t express why. At best it is in the comments 3) implicit internal requirements - core of how the how the app should work towards achieving your business constraints - code expresses what should be done but really can’t express why. At best it is in the comments
eg if item is “rocket” , shipping = $1m ( we only make rockets in Antarctica and shipping from there is $1m)
4) implicit external requirements - core of how the how the app should work towards achieving your business constraints - code expresses what should be done but really can’t express why. At best it is in the comments
eg if item is “rocket” , add a 3 month gating stage to get approval from government to sell the item and do not collect payment till gating approved - AI can see the code but has no idea why it has to be done
These come from partners, regulation, compliance, auditability etc
So, my theory
AI can be good at the explicit stuff trivially (1, 2) but cannot be good at the implicit stuff (3,4)
It might be able to figure out implicit stuff needs to be done but will probably not be able to figure out why it needs to be done and it will definitely not be able to definitively figure out edge cases for when to do it / not do it
As long as you focus on implicit stuff, you will be fine for a little bit
TL;DR - become good and keep being good at being the person who understands the implicit external drivers of software dev
Re: LLMs are eroding my software engineering career and I don't know what to do
#576Earlier quoted context omitted.
a year ago I would have agreed, but the gap is getting smaller all the time... these things can do 90% of the work, and how many people does a company really need for the remaining 10%? certainly not as many as they needed before
The things can do 90% of the work ... but only if used by the right people. I've seen first hand what less experienced developers produce using the same models, your 90% accuracy suddenly drops to 50%...
sure but even if it's one talented dev doing work that 2 would have done before... where's that work going to go? I don't think we need twice the amount of software
Re: LLMs are eroding my software engineering career and I don't know what to do
#577Maybe denial is a river in Egypt, but I (most of the time) believe that the glass is half full and we will need MORE humans as LLMs gain in ability. My thesis: 1. most jobs are created by small to medium size enterprise 2. the throttle for new SMEs has been people, money and ideas, in that order 3. with LLMs being a force multiplier, fewer technical people are needed but some people still ARE needed 4. with less thro…
Software boom due to SMEs looks very unnatural to me, because what makes software so special is its ability to scale, so it naturally tends to monopolization
Re: LLMs are eroding my software engineering career and I don't know what to do
#578Earlier quoted context omitted.
The corporations and executives are already winning if you swallowed the concept of 'rockstar' engineer. Sure there are more and less experienced engineers, but even interns can and often do provide good input and spot mistakes made by seniors. The 'rockstar' engineer at most tech companies simply equates to the somewhat autistic guy with a brown nose who's working 15 hour days for a pat on the head from management (…
For the most part there aren’t 10x engineers But there are certainly 0.1x engineers
The study that defined the 10x engineer defined him as 10x as good as the worst engineer. If there is a 0.1x engineer, and a 1x engineer, that 1x engineer is the very definition of a 10x engineer.
Re: LLMs are eroding my software engineering career and I don't know what to do
#579Earlier quoted context omitted.
I agree but I think it would take awhile. Some of us here seem to believe 2026-2027 is the end of programming jobs. At least that's Amodei seemed to be saying but then changed his mind later on?
Well given the pace of improvement so far, it's possible - though not given, IMO - that before 2028 we'll have models that make programming jobs fully obsolete. But that doesn't mean jobs will suddenly disappear; many places, especially in 3rd world countries, will continue to have humans programming for a while yet. Just that the available positions will slowly taper out over several more years, until only the most…
It's possible , yes. For now I'm betting against it, we'll see.
Re: LLMs are eroding my software engineering career and I don't know what to do
#580Earlier quoted context omitted.
> That sounds more like a problem of close minded narrow focus on economic output instead of culture, virtue and spiritual traditions. I’m starting to be more sensitive to the argument that without god, people are unable to have a strong moral foundation. Not for the people expressing creativity in how they fuck, but as a check on those in power.
It takes a special kind of issues-riddled mind in very unhealthy place, for the lack of better words, to assume that people without strong faith have less morals. In my own experience such people are often far from objectively moral or good people themselves, and overcompensate some deep issues.
> In my own experience such people are often far from objectively moral or good people themselves, and overcompensate some deep issues.
It is very true in my experience. It is also very not true in my experience.
FWIW I’m an atheist. Curious what you mean by issues-riddled mind. What issues? What’s the unhealthy place? There is no one person I’d accuse of lacking morality through godlessness, but I do see a trend. Most particularly in the people and communities who would have previously chosen godliness and replaced it with nothing, not those who previously would have chosen godlessness.