Viewing profile — pablomendes

As large language model (LLM) agents increasingly undertake digital work, reliable frameworks are needed to evaluate their real-world competence, adaptability, and capacity for hum…

In what kinds of workloads or usage patterns do you see the biggest performance gains vs traditional FaaS + storage stacks?

What does the tech stack look like?

Is the course focused on LLMs used to generate text or does it also talk about other kinds of testing like search, images, etc?

Cool! What's next in the roadmap?

Congrats on the launch! I'm an inveterate search nerd so I can't help but ask how did you implement search?

Hey there HN, I'm Pablo from Objective. We're working on an AI-native Search platform. Today we're releasing Anton ( https://www.objective.inc/anton ) an API that you can use to ev…

What are you using for the search tech?

That statement is both kind of true and, well, revisionist. Originally there was a strong focus on logics, clean comprehensive modeling of the world through large complicated ontol…

One thing that works well for me is going working-to-working. Get a simple, de-scoped, incomplete, probably crappy version done end-to-end. Now it's not about finishing, it's about…

Hey @afandian, can I interview you about the tech stack you all used to build search at Crossref.org?

Are you planning to implement search and filter tags?

How did you implement snippet search?

Happy to exchange notes with you on our learnings building https://podsearch.page

You might want to try semantic search instead of fiddling with keywords. Disclaimer: I'm building a plug-and-play semantic search API at https://kailualabs.com