undefined | Better HN

0 pointsjohnnyanmac15d ago0 comments

> I'm significantly faster while guiding an LLM using this methodology.

https://metr.org/blog/2025-07-10-early-2025-ai-experienced-o...

>When developers are allowed to use AI tools, they take 19% longer to complete issues—a significant slowdown that goes against developer beliefs and expert forecasts. This gap between perception and reality is striking: developers expected AI to speed them up by 24%, and even after experiencing the slowdown, they still believed AI had sped them up by 20%.

If we're being honest with ourselves, it's not making devs work faster. It at best frees their time up so they feel more productive.

0 comments

intelkishan15d ago

There's a new report from the same group which shows that the degree of slowdown has reduced. Link: https://metr.org/blog/2026-02-24-uplift-update/

rectang15d ago

Fair point. I have definitely caught myself taking longer to revise a prompt repeatedly after the AI gets things wrong several times than it would have taken to write the code myself.

I'd like to think that I have this under control because the methodology of working in small increments helps me to recognize when I've gotten stuck in an eddy, but I'll have to watch out for it.

I still maintain that the LLM is saving me time overall. Besides helping in unfamiliar domains, it's also faster than me at leaf-node tasks like writing unit tests.

tmaly15d ago

How long will that 19% hold as models grow in capability?

johnnyanmacOP15d ago

I'm a bit tired of waiting for "tomorrow", so I'll just live in today's world. We'll burn that bridge when we get to it.

rafaelmn15d ago

The study you quoted is sonnet 3.5/3.7 era. You could see the promise with those models but the agentic/task performance of Opus 4.5/4.6 makes a huge difference - the models are pretty amazing at building context from a mid size codebase at this point.

1 more reply

j / k navigate · click thread line to collapse