Matt Collins
@mattcollins.net
CTO, Product Builder & AI/LLM Enthusiast • London, UK
www.mattcollins.net
www.mattcollins.net
I agree it's not getting the attention it deserves.
Perhaps it'll take someone exploiting this at scale (hopefully in a fairly harmless way) to jolt us to our senses a bit.
Perhaps it'll take someone exploiting this at scale (hopefully in a fairly harmless way) to jolt us to our senses a bit.
September 8, 2025 at 2:48 PM
I agree it's not getting the attention it deserves.
Perhaps it'll take someone exploiting this at scale (hopefully in a fairly harmless way) to jolt us to our senses a bit.
Perhaps it'll take someone exploiting this at scale (hopefully in a fairly harmless way) to jolt us to our senses a bit.
And for discussion of more sophisticated, at-scale stuff, I thought this talk was good: www.youtube.com/watch?v=cZ5Z...
Mission-Critical Evals at Scale (Learnings from 100k medical decisions)
YouTube video by AI Engineer
www.youtube.com
March 4, 2025 at 10:43 AM
And for discussion of more sophisticated, at-scale stuff, I thought this talk was good: www.youtube.com/watch?v=cZ5Z...
I think a helpful early step is to put in place a way to run some very simple automated evals. That lowers the 'activation energy' to add more.
Like traditional tests, it takes discipline to add and maintain these evals but without them you don't know what you're breaking / making worse.
Like traditional tests, it takes discipline to add and maintain these evals but without them you don't know what you're breaking / making worse.
March 4, 2025 at 10:36 AM
I think a helpful early step is to put in place a way to run some very simple automated evals. That lowers the 'activation energy' to add more.
Like traditional tests, it takes discipline to add and maintain these evals but without them you don't know what you're breaking / making worse.
Like traditional tests, it takes discipline to add and maintain these evals but without them you don't know what you're breaking / making worse.
If it wasn't open source, maybe another IDE's ecosystem would be dominant which would be worse for them.
January 20, 2025 at 3:03 PM
If it wasn't open source, maybe another IDE's ecosystem would be dominant which would be worse for them.
Repo here: github.com/openai/opena...
GitHub - openai/openai-realtime-agents: This is a simple demonstration of more advanced, agentic patterns built on top of the Realtime API.
This is a simple demonstration of more advanced, agentic patterns built on top of the Realtime API. - openai/openai-realtime-agents
github.com
January 17, 2025 at 4:27 PM
Repo here: github.com/openai/opena...
Best of luck with the new venture!
November 14, 2024 at 1:10 PM
Best of luck with the new venture!
Wow, sorry to hear that - sounds rough. I'm glad to hear a bit of coding is helping. We live in good times for tinkering!
November 14, 2024 at 11:03 AM
Wow, sorry to hear that - sounds rough. I'm glad to hear a bit of coding is helping. We live in good times for tinkering!