Recent submissions

Comment · 5 days ago
Why would anyone take the offer if it's so vanilla? You'd be at a disadvantage to leave in a large wave like this; better to wait and be laid off in a smaller group and get the same package.
Comment · 6 days ago
100/m for a subscription is a lot of money to most people. Like people who don't have a SWE salary.
Comment · 12 days ago
It's no different than having a human editor.
Comment · 1 month ago
Hypothesis Driven Development would beg to differ.
Comment · 1 month ago
I think System 1 is a great term. System 1 is fast, intuitive, and automatic. It describes decision-making that happens without explicit reasoning or deliberation. System 2 is the opposite: it's the more deliberate, "executive functioning" side of cognition -- the part that reasons through a problem before arriving at an answer. That's also what state-of-the-art LLMs do before they respond. Jev doesn’t do that kind of reasoning. It just decides.
Comment · 1 month ago
> But the moment you build your own agent, you’re on your own. It’s tricky wiring up the right primitives just well enough to match that “it just worked” feeling.

It's wild to me to claim that it's tricky to customize one of these harnesses and for that to be the entire justification for an entirely different harness.

It's really not that hard. If you want to reduce costs then all you need to do is practice delegation: instead of using the strong model, all the time to do everything, instead, you have the stronger model delegate well-defined tasks to a weaker model. Patterns like these are really easy to wire up.

Comment · 1 month ago
It wasn't
Comment · 1 month ago
You call it a guess, I call it a hypothesis.
Comment · 1 month ago
After you sure that isn't because your skin is moist where sunblock was recently applied, and therefore cooler?
Comment · 1 month ago
To me, one interesting piece of analysis was whether Luna had benefit on top of Astra -- i.e., running both and synthesizing their findings. But even with that, it raises the question whether running a second Astra pass, or Sol, or even a model from another family (GLM? Fable?) would deliver even more additive benefit.
Comment · 1 month ago
My thoughts exactly. That 22pp gap is massive, and it seems to me Astra is worth every extra penny.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton