hommes-r

Joined 2 years ago

Karma
7
Submissions
28
Member since
Jul 8
Founder of an agent reliability engineering startup. We are a VC-backed company that works with RL, fine-tuning, MCP and agents.

Agents in production fail unpredictably, and you only know when customers complain. We find root causes and help you fix what matters, turning issues into reliable agent behaviour.

Feel free to reach out: [email protected] https://moyai.ai

View on Hacker News

Recent submissions

Comment · 2 months ago
Moyai Agent Reliability Engineering
Comment · 6 months ago
Comment · 8 months ago
Comment · 9 months ago
Comment · 10 months ago
I would add that "extremely sound data engineering" is also necessary to make observability cost-effective. Some of these otel platforms can burn 10%-25% of your cloud budget to show you your logs. That is insane.
Comment · 11 months ago
Comment · 11 months ago
"Because there’s too much you need to feed into it" - what does the author mean by this? If it is the amount of data, then I would say sampling needs to be implemented. If that's the extent of the information required from the agent builder, I agree that an LLM-as-a-judge e2e eval setup is necessary.

In general, a more generic eval setup is needed, with minimal requirements from AI engineers, if we want to move forward from Vibe's reliability engineering practices as a sector.

Comment · 11 months ago
Just another example of money scaling your way out of a problem. What you don't understand is hard to optimize. Like how you have solved this by acting as an smart router in between that first understands what to optimize and then actually implement that optimization.
Comment · 1 year ago
Comment · 1 year ago
My personal opinion is that true engineering, which revolves around turning complex theory into working practice, has seen a decline in grace. Why spend a lot of time trying to master the art of engineering if you can ride the wave of engineering services and get away with it?

In true hacker spirit, I don't think trying to train a model on a wonky GPU is something that needs an ROI for the individual engineer. It's something they do because they yearn to acquire knowledge.

Comment · 1 year ago
Comment · 1 year ago
Awesome to see the Cursor Airweave example!
Comment · 1 year ago
Sad to see the "change world GDP" mantra didn't trickle down to the people doing the actual plumbing.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton