News for hackers. Stuff that matters.
Re:2x, not 10x: coding with LLMs in 2026 by watso on Thursday July 30, 2026 @03:49PM (#49114856)
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?
Re:2x, not 10x: coding with LLMs in 2026 by peheje on Thursday July 30, 2026 @04:26PM (#49115296)
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 by watso on Wednesday August 05, 2026 @04:28PM (#49188536)
So you don't think fundamentals built by actually coding will be necessary to produce well structured and maintainable code with an LLM?
Re:2x, not 10x: coding with LLMs in 2026 by ipaddr on Thursday July 30, 2026 @05:19PM (#49115943)
In 10 years llms will handle it all from start to finish.
Re:2x, not 10x: coding with LLMs in 2026 by kazinator on Thursday July 30, 2026 @05:21PM (#49115972)
We have passed peak LLM already. In 10 years, something might be handling "it all" from start to finish, but it won't be LLMs.
Re:2x, not 10x: coding with LLMs in 2026 by swordsith on Friday July 31, 2026 @07:50AM (#49121971)
Saying we're at the Peak of LLMS is like saying we never went further than everest, these are probabilistic state machines sure, but the real value is the effort put into tooling and training these models in RL situations.