Comment by oytis
14 days ago
Absolutely. I'm gonna go full agentic coding the day I can do it with open-weight models on my machine. Until then feeding someone else's models with more data on how to replace me in particular sounds insane to me.
14 days ago
Absolutely. I'm gonna go full agentic coding the day I can do it with open-weight models on my machine. Until then feeding someone else's models with more data on how to replace me in particular sounds insane to me.
If you think it's going to replace you, then it's going to replace you regardless of whether you personally are feeding it data or not.
If it produces value for you, you should use it. If not, don't.
So far I have been able to trade some efficiency for more control in my professional life. All of my tooling is open-source and local. I hope I can get away with it this time as well though sure some adjustment will be needed
But why? Why not simply do/use whatever is most cost-effective? In the places where greater control leads to less efficiency, what is the benefit of control?
This is a genuine question -- I really don't understand. I appreciate local tooling when it helps my long-term efficiency, even if there's a learning curve. But not if cloud seems like it will always be more efficient. And while there are LLM's you can run locally, it doesn't seem like the ones useful for coding, with their vast memory and GPU requirements, will be realistic or cost-effective to run locally in the foreseeable future.
4 replies →