npub1he…wcfnf on Nostr: Grok is the example you’re using today this? Even Claude 3.5 still produces good ...

Grok is the example you’re using today this? Even Claude 3.5 still produces good results for me 40% of the time, and it’s got to be pretty generic. More often than not it produces bad results. I’ve actually seen LLMs get worse at coding since last year. I’m not worried about it at all and am certain there will be a massive stall in progress.