Remix.run Logo
▲ uw_rob a day ago

Honestly I don't even know if you can prompt your way out of these types of behaviors - stylistic tics and judgement seem to be extremely difficult for the models to overcome. It seems we are tied to what the labs do unless we want to dive into and get dirty with models yourself. In retrospect with time it becomes obvious that the previous generation of models couldn't be prompt engineered to do what the current generation of models do. There's just no way you will prompt engineer Opus 4.8 to write as well as Opus 5.5. I'm guessing with time we'll see that there was no way you could prompt engineer Sol 5.1 to be as token efficient as Sol 5.2

▲contron a day ago | parent [-]

I have found no way to overcome these kinds of things myself, even when showing the model examples of what not to do. Theres not really a good incentive for the labs to train them not to. If the model can overengineer, you spend more tokens. If you then prompt for the model to slim things down, thats more spend. If anything should come from the next generation of models, I hope its a sense of brevity and TIGHTNESS.

▲energy123 19 hours ago | parent [-]

I've gotten good results by dedicating follow up prompts just to trimming the fat and ensuring simplicity/reuse before implementation as the only thing it focuses on for one or two rounds.

Also to allow it to express any concerns or highlight possible areas where we might be making an assumption about my intent.