Diana Hu
speaker
322 appearances
4 recordings
1 series
first heard Jun 2026
last heard 5 Aug
Diana Hu’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsRecordings per month over the last 12 months — 4 in all, peaking in Aug 2026 with 2.
Appearances
Because in order to have the data to be fully lossy and compress it and then restore it, you basically need to understand it.
And now transformer architecture is basically one of the ways that has turned out to work really well.
Working pretty well so far.
Yes.
Now, let's zoom out a bit.
AI progress used to mean just better models.
You had more data, trained bigger models with bigger parameters.
But increasingly in the last years or so, it's everything around the model, not just the model size and number of parameters or more data.
It's everything around things like retrieval, tools, memory, agent tools.
And it might kind of get consolidated into what people call context engineering, right?
And I think the fun thing about this particular problem domain set is actually something that everyone in this room can actually do.
Because before, to train a model, you needed incredible amount of resources, incredible amount of access to GPUs and data.
But for context engineering, everyone here could do it.
You just need the API to something like Gemini, and then work on your own setup for your own retrieval, your own tool calls, and et cetera, et cetera.
What are some tips for everyone here?
How does everyone get better at and become exceptional at context engineering?
Can you give an example of some context engineering you personally have done?
I don't know, skills you wrote, tools that really made a huge difference in your workflow.
Wow, that seems very impressive.
So you're saying you have this skill that if someone got access to it, it could perform optimizations like Jeff Dean.
Showing 101–120 of 322 · page 6 of 17
← Previous
Next →