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

Post by jatora » Fri, Jul 31, 2026, 4:50 AM UTC

overfeed wrote: post #87

pantelisk wrote: post #55

While I agree with the premise, I think this angle only applies on work one was going to do no matter what. The real power of these tools is that there are so many ideas people would like to try, but never have the time or motivation to pursue. So the comparison is not only "built with and without LLM" but "would you even build this if you didn't have the LLM?". The gap in productivity in this case is much more wide.

> The real power of these tools is that there are so many ideas people would like to try, but never have the time or motivation to pursue. This can be a negative multiplier: code I thought I wanted that gets immediately abandoned is a net-negative if no one else wants it (lets face it, this is the safest default posture for software of unknown providence). In isolation, instant-abandonware takes up hdd space, burns d…

Post by SkyPuncher » Fri, Jul 31, 2026, 5:17 AM UTC

dools wrote: post #154

serial_dev wrote: post #83

Earlier quoted context omitted.

> it produces some extremely crappy code that would've NEVER passed a code review 1 year ago The 10x speed up comes from the fact that we have all given up on properly reviewing each others code and we just say “meh, it will be fine, lgtm”

Code review has always been pointless

Post by bdcravens » Fri, Jul 31, 2026, 5:26 AM UTC

xXSLAYERXx wrote: post #179

RegW wrote: post #137

Earlier quoted context omitted.

Where as I'm stuck in a big team with a legacy codebase and lots of business rules, performing small incremental changes. So I spend my days banging the Esc key and shouting "Shut the f**k up!". Luckily I work remote. I'd turn it off again, but my usage is monitored and I don't want to look like a Luddite. So may be .75x to .8x range.

In my experience a legacy codebase is where LLM shines. What would take days to grok is understood and explained almost immediately. There was a bit of job security with being the one whose worked with IIFEs to manage state. You must know the codebase well if the LLM is slowing you down.

Post by stephenr » Fri, Jul 31, 2026, 5:32 AM UTC

t-writescode wrote: post #190

Xcelerate wrote: post #187

I have a weird issue with using AI for coding. I can code something entirely by myself at my baseline speed; call it 1x. Or I can use Claude to do it, and it does it in 1/10 - 1/4 of the time. The problem, however, is that to review Claude’s code properly takes 2-3x the amount of time it would have taken me to write it all by hand. So my two choices are basically “YOLO, LGTM” and hope I can revert if it breaks someth…

This is what I've seen. There has been a middle-ground though, that I've seen. I was using Jetbrains' AI Assistant, or whatever it's called, during an interview for the (nearly) first time, and I only used it as auto-complete, but it was consistently, surprisingly, very accurate. I literally did write it faster. I scanned the literal next line, in the context of what I was writing, with all that context in my brain,…

Post by encyclopedism » Fri, Jul 31, 2026, 5:34 AM UTC

HarHarVeryFunny wrote: post #131

Even if that 2x were a representative number (although another HN story today says 1.1x - 10% improvement), what really matters is whether companies are overall seeing any AI spending return on the bottom line. There is a lot of reason to suspect that at most companies, especially more established non-startup ones, there will close to zero bottom line benefit, because these companies already have free paid-for develo…