Re:I Cancelled Claude: Token Issues, Declining Quality, and ...
by flyinglizard on Saturday April 25, 2026 @06:33AM
(#47900325)
Try asking to review your code as if it were Linus Torvalds. No, really.
Re:I Cancelled Claude: Token Issues, Declining Quality, and ...
by sarchertech on Saturday April 25, 2026 @11:56AM
(#47902405)
I’ve tried that. I’ve experimented with a whole council of 13 personas including many famous developers. It’s definitely different. But it’s hasn’t performed significantly better in my tests.
Love this paragraph; it's exactly how I feel about the LLMs. Unless you really know what you are doing, they will produce very sub-optimal code, architecturally speaking. I feel like a strong acumen for proper software architecture is one of the main things that defines the most competent engineers, along with naming things properly. LLMs are a long, long way from having architectural taste