HN user
I suppose, although the trust is doing a lot of work, not just in "can this work as I want today" but "can this consistently work for the next x years" which is a very different problem to solve for. But we'll have to see the roll out on this.
We’re introducing OpenAI Presence, a battle-tested product Proven through years of working with customers at enterprise-scale
I don't want to laugh too hard this afternoon. But more seriously, I'm not really sure who this product is for in a way an existing tool can't handle? Like if a business really wants to go deep on agentic workflows for customer service, what is going to make them reach for this?
To improve determinism, define a system instruction with explicit rules for your specific use case.
Is this guaranteed to work any better than top_k or top_p? This just sounds like making a smaller version of a Agent.md doc.
Very interesting thought experiment. One thing I'm curious is how you might think through scale, certain data formats scale much faster and may consume more space than others. How do balance both growth of data formats and overall how much data can be hosted?
Location: Orlando, FL
Remote: Yes
Willing to relocate: Yes
Technologies: Python, C/C++, Rust, Javascript/Typescript, React, Java, SQL, Azure, AWS, PyTorch, TensorFlow, Circuit Design, Embedded Systems, Microcontroller Programming, x86 Assembly, VHDL
Résumé/CV: https://drive.google.com/file/d/1ZIJVmLeNlBIYkhc7h3lAtarvEJg...
Github: https://github.com/ColonelToad
Email: chrisonyiuke@gmail.com