Hacker News Reader

Knowledge graph is more of an expert system in terms of how it i updated and it's data sources. There isn't much magic there, so I doubt bard could get much from it if it's capable of being trained on unstructured web content.

The more likely dependency would be bard ingesting unstructured data and generating structured data to update knowledge graph with.

They should be able to use it to check for contradictions against what the Bard has generated and facts in the KG.

For example I asked chatGPT about birds that can't fly and it started bullshitting about all sorts of birds that clearly can, those facts would likely be in the KG.

I dunno - Google assistant relies heavily on the KG and it's pretty garbage - but then that could be more to do with Google Assistant than the quality of the KG.