Re:Coding with LLMs in the summer of 2025 (an update)
by generic92034 on Sunday July 20, 2025 @02:54PM
(#44628162)
> and a subscription to $paid_llm_of_choice is _cheap_ relative to my time spent working.
In the mid to long term the question is, is the subscription covering the costs of the LLM provider. Current costs might not be stable for long.
Re:Coding with LLMs in the summer of 2025 (an update)
by RugnirViking on Monday July 21, 2025 @02:21PM
(#44638566)
That is, in every sense of the term, their problem.
I will switch to whatever is best for me at a good price, and if thats not sustainable then I'll be fine too; I was a developer before these existed at all, and local models only help from there.
Re:Coding with LLMs in the summer of 2025 (an update)
by jakebennet89 on Monday July 21, 2025 @07:31AM
(#44633970)
Exactly. Local setups are fun to tinker with, but when you’re deep in a project, you just want things to work fast and stay out of your way.
In my experience, something Llama 3.3 works really well for smaller tasks. For "I'm lazy and want to provide minimal prompting for you to build a tool similar to what is in this software package already", paid LLMs are king.
If anything, I think the best approach for free LLMs would be to run using rented GPU capacity. I feel bad knowing that I have a 4070ti super that sits idle for 95% of the time. I'd rather share an a1000 with bunch of folks and have that run at close to max utilization.