Hacker News Reader

>> My guess would be that the training data differs just enough for it to have an impact.

It's because performance degrades over longer conversations, which decreases the chance that the same conversation will result in a solution, and increases the chance that a new one will. I suspect you would get the same result even if you didn't switch to a different model.

View on HN

So not really, certainly models degrade by some degree on context retrieval. However, in Cursor you can just change the model used for the exchange, it still has the same long context. You'll see the different model strengths and weaknesses contrasted.

They just have different strengths and weaknesses.

if claude is stuck on a thing but we’ve made progress (even if that progress is process of elimination) and it’s 120k tokens deep, often when i have claude distill our learnings into a file.. and /clear to start again with said file, i’ll get quicker success

which is analogous to taking your problem to another model and ideally feeding it some sorta lesson

i guess this is a specific example but one i play out a lot. starting fresh with the same problem is unusual for me. usually has a lesson im feeding it from the start

Reply on news.ycombinator.com