Recent submissions

Comment · 2 days ago
your username's not orange.
Comment · 1 month ago
What's the benefits of this over traditional GKE pub/sub, kafka or another queuing service?
Comment · 1 month ago
Comment · 1 month ago
Thought I was going crazy, glad to know I wasn't the only one.
Comment · 2 months ago
If you're getting fired in 2 weeks, it's likely not because of a single comment.
Comment · 3 months ago
10% cheaper than official! Let the inference pricing wars begin!
Comment · 5 months ago
Genius I love it!
Comment · 6 months ago
Are you guys going to follow up with a paper showing EDEN results match or beat turboquant for needle in a haystack benchmarks?
Comment · 7 months ago
With AI you actually don't need to choose anymore. Well laid out abstractions actually make AI generate code faster and more accurately. Spending the time in camp 2 to design well and then using AI like camp 1 gives you the best of both worlds.
Comment · 7 months ago
Extrapolating the benchmarks, this would imply the best RYS 27B is capable of out performing the 397B MoE?
Comment · 7 months ago
super clever and awesome!
Comment · 7 months ago
The freeze sometimes does capture in between states. What I've seen the agent does in those cases is that it recognizes it's in between states and calls browser_wait(). Where the agent goes off the rails isn't a snapshot in the middle of a state transition, (it's smart enough to know to retry in that case), it's when the DOM changes after the agent believes the page has settled.

For async, lots of people smarter than me working on the smarter agent problem. Though there's a latency floor with inference due to prompt processing, and output generation. Without tools like ABP, the LLM is always aiming at a moving target.

Comment · 7 months ago
*bows
Comment · 7 months ago
It's a long shot but getting ABP to be a first party citizen alongside CDP would be my dream!
Comment · 7 months ago

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton