Comment by lacoolj

5 days ago

I love everything about this launch post. They feel like people i would get along with.

And i already sub to jev and i think this launch is going to make me a much more loyal user now lol

> We’ve heard you loud and clear on context lengths. Jev actually supports a much longer context length than we’ve enabled in production. We chose to limit it intentionally because Jev, like all models, is less reliable on longer contexts, and this constraint encourages more effective usage patterns in prod.

> We aren’t your parents though, so while we strongly recommend limiting context length, you no longer have to:

> TypeSafe-Danger-Zone-Long-Context: true

For me it's the reverse, it gives very shady vibes.

Remember the relatioship incentive is skewed, you are giving in your precious data inexchange for random logprobs, that they offer to "cheap".

  • They’re upfront about their decisions and intentions. All of which make perfect sense. What gives it shady vibes for you?

    Eg: Longer context has long been known to reduce response accuracy, so it makes perfect sense why they’d limit it especially at launch. Personal evals are in fact more useful than public benchmarks so it makes sense (and is refreshing) that they’re cautioning against them…

I had the opposite feeling tbh

"...there's no way that our team has a full understanding of what is needed to spark delight in the world and build sick sci-fi."

"Size does matter, apparently "