rohit
@krishnanrohit
Essays: |
Book: |
Senior Fellow @wharton |
In Stealth
Joined December 2010
2.4K Following 32.7K Followers
Current models are so powerful that this problems gotten worse, because going in subtly wrong directions can be hard to detect! Y'day I realized that Astra had been running an eval on some random synthetic subset of the data instead of the bench, as I asked. Cost me a day!
Show more
