Ask HN: How is Bard able to use current news/data more quickly than ChatGPT?

It seems like ChatGPT has quite a large lag from their training set to when it goes to production, with no updates in between. But with Google Bard it seems like they are able to update their existing models for current events? What makes this possible and why can't ChatGPT do the same?

ChatGPT:

> what was the last fed rate hike?

> As an AI language model, my training cutoff date was in September 2021 and I do not have access to real-time information. However, I can tell you that the Federal Reserve's last interest rate hike occurred on December 16, 2020. At that time, the Federal Open Market Committee (FOMC) raised the target range for the federal funds rate by 0.25 percentage points to a range of 0.25% to 0.50%. This was the first and only interest rate hike of 2020.

Bard:

> what was the last fed rate hike?

> The Federal Reserve raised interest rates by 25 basis points on March 22, 2023, to a target range of 4.75-5%. This was the ninth consecutive increase in interest rates since the central bank began the current rate-raising cycle to combat rising prices.