
OpenAI's o1 vs. GPT-4o: When to Use Each Model
While existing and new models showcase impressive capabilities, they are designed for different tasks and come with distinct costs

While existing and new models showcase impressive capabilities, they are designed for different tasks and come with distinct costs
While existing and new models showcase impressive capabilities, they are designed for different tasks and come with distinct costs
When scaling bebop pre- and post-acquisition by Google, we developed an approach to Product Review Meetings that made them productive discussion forums. This series details what we learned.
This is part 6 in an ongoing series of indeterminate length that explores how tech giants envision the future of AI-powered development
This is part 5 in an ongoing series of indeterminate length that explores how tech giants envision the future of AI-powered development.
This allows us a lot of flexibility in choosing which models we use and fall back from one to the other without any user impact
This focus stems from a lesson I learned the hard way as a young, inexperienced PM
One of the most surprising patterns I’ve seen is how many great product folks have asked… is there a way I should be doing this?