David Soria Parra
speaker
798 appearances
1 recordings
1 series
first heard Dec 2025
last heard 27 Dec
David Soria Parra’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 — 1 in all, peaking in Dec 2025 with 1.
Appearances
We're very early in the industry still.
We're learning a lot about like what does the model need, what does not need, right?
Um and even today, like
uh some agents start to like drop tool call results after a few rounds because they don't need it anymore.
And I think that's very, very, very good.
And so I think besides compaction, you will see I um just better mechanics of like understanding what you need and what you don't need.
Like for a long asynchronous test, you might have a a way where like okay maybe for a while the model sees it, but once you get the result, you just drop everything else.
Or you might
might might even call like a small model like a haiku model and go like what of this I should retain, tell me, right?
Like you might be like the AGI built approach would be just like let the model figure out what it needs to retain, right?
And so you can you can see both worlds and then and I think there's just lots to learn.
I think there's not the one answer yet because I think we're still figuring these type of things out and we're just improving.
And compaction compaction is is a good step for it.
But I don't think it's the last step there either.
It is actually the the most obvious one.
But I don't think it's like I think if you pay more attention to it, if you particularly think about like, okay, what could you train a model to do here?
I think we get to much better ways of doing that.
But they're all like independent from how you obtain the context.
And I think MCP I always see is like back to like it's an application layer protocol.
That's just how you obtain the context, how you select the context, that the problem
Showing 561–580 of 798 · page 29 of 40
← Previous
Next →