Viewing profile — cye131

I'm not a fan of this blog post as it tries to pass off a method that's not accepted as a good or standard time series methodology (graph transformers) as though it were a norm. Tr…

The new 2.5 Pro (05-06) definitely does not have any sort of meaningful 1 million context window, as many users have pointed out. It does not even remember to generate its reasonin…

I'm curious whether anyone's actually using Claude code successfully. I tried it on release and found it negative value for tasks other than spinning up generic web projects. For e…

These performance numbers look absolutely incredible. The MoE outperforms o1 with 3B active parameters? We're really getting close to the point where local models are good enough t…

R especially dplyr/tidyverse is so underrated. Working in ML engineering, I see a lot of my coworkers suffering through pandas (or occasionally polars or even base Python without d…

Does anyone actually have access to this? It says available for pro users on the website today - I have pro via my employer but see no "deep research" option in the message compose…

Is it accurate to compare 8k example RL with 8k example SFT? RL with the same amount of examples would take massively more compute than the SFT version (though depending on how man…

There is a surprisingly common use case for "quick and dirty univariate time series forecasts" that are basically equivalent to giving a small child a pencil, and asking them to dr…