Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

2x, not 10x: coding with LLMs in 2026

obryant.dev

Post reply on HN
Print view View original

41–50 of 260 posts

Re: 2x, not 10x: coding with LLMs in 2026

#41

Post by wannabe44 »

monknomo wrote: post #24
openasocket wrote: post #20

Earlier quoted context omitted.

+10, I can't stand AI-generated comments. Half the time they are paragraph-length translations of every 5 lines of code into English prose, or just regurgitating whatever prompt they were given. When they actually try making high level comments they are worse than useless. It's really hard to put into words exactly why. It's something about how they are very verbose, but at the same time vague and stated in a slightl…

locally correct and globally incoherent is how they seem to me. I, and a number of folks I have talked to, find some of them incomprehensible. Like each sentence makes sense, but the overall thing does not.

It's because they don't really have a mental model. RL with Verifiable Rewards can reward working code, but it can't tell you whether the prose make sense or not. In theory RLHF should be good with this. In practice, it appears to be a measure difficult to quantify and steer. I am not an insider though. So it's just a theory.

Re: 2x, not 10x: coding with LLMs in 2026

#42

Post by wongarsu »

troupo wrote: post #15

> Never write READMEs, docstrings, or comments. I found that latest codes don't write comments in code by default. And when they do, they write stupid shit like "This was code that did X, it was now removed". You have to explcitly prompt them to write comments in code. They are still useful for you, the user. But are arguably useful for the model, too, given how many of them (especially Claude) only reads small chunk…

A small mention in your user-wide Claude.md (or Agents.md or whatever you use) about the desired types of comments goes a long way. The typical "why, not what", clarifying larger-picture stuff, and everything else you find in every book on code quality

Re: 2x, not 10x: coding with LLMs in 2026

#43

Post by rglover »

I mean the "x amount" is relative to your existing skill level, right?

It's worth asking ourselves "why does the x amount matter?" I get the desire to define KPIs to estimate productivity gains. But this all seems to be—rather rapidly—leading to an increasingly dehumanized reality (both figuratively and literally) so we can...produce more software? I love building software, and I enjoy using LLMs to help me do it, but there's just this weird vibe I can't quite shake about how we're trying to quantify all of this.

Re: 2x, not 10x: coding with LLMs in 2026

#44

Post by wannabe44 »

tristor wrote: post #25

My observation is that AI tools generally make people /less/ productive. They are more productive in that they produce more stuff, but they are less productive in that the stuff they are producing has lower inherent value delivery. The primary place where I see this in software teams as a Product person is in document creation. If you are using an AI tool to produce internal documents, this is likely a net-negative v…

Have you worked with codebases where people produced slop even before LLMs? In such codebases LLMs are a godsend. They can churn around huge amounts of code and find needles in the haystack.

Re: 2x, not 10x: coding with LLMs in 2026

#46

Post by altern8 »

gashad wrote: post #5

This reminds me of themes I recently saw in [Harness Engineering is not Enough: Why Software Factories Fail]( https://www.youtube.com/watch?v=Ib5GBkD555M ) (Warning: the last 3 slides seem like an advertisement). One thing I liked is how Dex has a little graphic he glossed over showing software development is - 25% planning & aligning with other teams - 25% coding - 25% testing/verifying - 25% code review/rework One…

AI is great because my job is a lot easier, but it produces some extremely crappy code that would've NEVER passed a code review 1 year ago.

You could argue that it speeds up development by 5X or more, but then it slows down testing/verifying, code review, and in many cases it makes it impossible to review/rework by hand.

I just do what I'm told at work but even though I'm sure I'm in the minority I'm extremely skeptical that LLMs can produce any good-quality code.

Looks to me like we've just lowered the bar--by a lot--and stopped looking at the code that goes out. Every time I look into how Claude implemented something it's completely insane, with no way to refactor it or maintain it in the future.

Re: 2x, not 10x: coding with LLMs in 2026

#47

Post by peheje »

watso wrote: post #26

You still have to know what you’re doing. That came from years of doing it by hand. Where is that necessary experience going to come from for the current and future generations of juniors?

Shipping. Breaking stuff. Fixing it. And discovering, repeatedly, that the tool sounded much more confident than it had any right to.

Like always. This is why the average carpenter you hire in 2026 still won’t do a perfect job, despite carpentry having existed for thousands of years.

Re: 2x, not 10x: coding with LLMs in 2026

#49

Post by jdlshore »

iLoveOncall wrote: post #2

Even this is overstating it IMO. I already convert from multipliers to percentage of increase, so when someone claims 10x they very likely mean +100% productivity, and here 2x means +20% productivity, which seems about right. Nobody that was normally productive before LLMs has suddenly 10x'ed their output now. The problem is that 20% productivity when it comes to generating code, really doesn't translate in 20% produ…

2x is 100% increase.

Re: 2x, not 10x: coding with LLMs in 2026

#50

Post by smashinlabs »

More than 2x for me. The models are accelerators, but the biggest gains came from building workflows around them. I spend most of my time documenting what I want, while implementation and much of the surrounding work become relatively cheap. I've found that AI amplifies engineering experience more than it replaces it. The better you are at framing problems and evaluating solutions, the more productive it becomes.
Post reply on HN