Thread

Introducing System One Models and Jev

1989 points · 520 comments · albelfio

tylermarques · 1789506204 · focus · HN ↗
We had early access and found it to be pretty useful. Having a second form of verification, where you can ask multiple questions (in the form of Nouls) raised our confidence in the outputs of other models. [0] IMHO This type of model works incredibly well in concert with LLMs, not as a replacement.
[0] <a href="https://goodstartlabs.com/research/verification-is-the-bottleneck" rel="nofollow">https://goodstartlabs.com/research/verification-is-the-bottl...
1. kevmo314 · 1789541782 · focus · HN ↗
  Don't your numbers suggest DeepSeek V4.1 Flash, for $100 more, gets you to slightly better agreement?
  1. tylermarques · 1789582756 · focus · HN ↗
    Yes they definitely do - not claiming it's a perfect solution, but as a V1 product it shows a lot of promise.

Unofficial Hacker News client; not affiliated with Y Combinator.