SilenN

Joined 7 years ago

Karma
176
Submissions
62
Member since
Sep 5
silennai.com github.com/SilenNaihin
View on Hacker News

Recent submissions

Comment · 3 days ago
Congrats!!
Comment · 2 months ago
"Anonymous aggregate PostHog product telemetry is enabled by default. It never includes prompts, traces, actions, observations, paths, model names, credentials, or raw customer content."
Comment · 2 months ago
We had this exact problem so we solved it for ourselves. Happy to help if you run into any issues.

I have a /hmmm command I use for the second part that works reasonably well: "Stop using jargon and speak coherently. State it more simply and concisely, like one human talking to another. Make it like google dev docs style. More dead prose. No aphorisms, no flourishes. Simple."

Comment · 2 months ago
Thank you!
Comment · 2 months ago
Thanks for the positivity tyre! If you look at our git history, we pivoted and only started building the gateway recently. Before that we were building research infrastructure that now powers the intelligence features we provide.
Comment · 2 months ago
Telemetry is off by default. PostHog is for usage analytics on the open source repo. Audit it if you're skeptical.

We make money off enterprise licenses and hosting models.

I have strong reason to suspect you either can't read or are a bad actor.

Comment · 2 months ago
Yep! One interesting example is often Opus 5 on low reasoning ~= Opus 5 on high reasoning.
Comment · 2 months ago
See you soon
Comment · 2 months ago
Ans: we rarely switch, often times it's just a "switch to using this model for your agent"
Comment · 2 months ago
Also a hosted marketplace, not just BYOK
Comment · 2 months ago
That is another way to do. Or we can automatically figure out which models the subagents should be using for you. And update them as new models come out and the work your subagents do changes. More than one way to skin a cat.
Comment · 2 months ago
Yep! If you look at the commit history that's exactly what happened.
Comment · 2 months ago
The trick is to rarely switch, or switch at task boundaries. Often the conclusion of routing is actually "this one model is actually at the pareto front for this task, just use it always".
Comment · 3 months ago
^this

There's two ways to functionally measure this, reconstruction fidelity (which we're able to get to 0.7 - 0.95), and downstream performance (which agrees on the best and worst models, but can sometimes disagrees on the middle of the pack routing).

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton