Thread

1. hbarka · 1789982542 · focus · HN ↗

   If Jev is fundamentally trained using RLCD while you’re building on a Qwen model that was trained using RLHF, how can the resulting model be considered Jev-like?

   1. mohsen1 · 1789986029 · focus · HN ↗

      I can't find it but saw that if you give Jev English alphabet as choices and ask it in a loop what model it is, it would say Qwen

      also tried myself: <a href="https:&#x2F;&#x2F;console.typesafe.ai&#x2F;playground?share=shr_1690a3160f19c2e4851b6a2883bcf17a790" rel="nofollow">https:&#x2F;&#x2F;console.typesafe.ai&#x2F;playground?share=shr_1690a3160f1...

      1. bityard · 1789993110 · focus · HN ↗

         That is not how models work.

         Unless specifically told in a system prompt, the pile of weights has absolutely no knowledge of itself. You could hypothetically train it to answer such questions, but nobody bothers to do this, and ALL &quot;knowledge&quot; embedded in the weights is probabalistic anyway.

         (I feel like this should be common knowledge in LLM discussions on HN by now.)

         1. tlb · 1789993737 · focus · HN ↗

            &quot;&lt;Q&gt;What model are you?&lt;A&gt;Qwen.&quot; is surely in Qwen&#x27;s training data. It&#x27;s quite standard to include such meta knowledge during instruction tuning.

Unofficial Hacker News client; not affiliated with Y Combinator.