Thread

1. Oras · 1789820747 · focus · HN ↗

   I played around with Jev last night and did it for classification tasks that I used Gemini 2.5 flash lite with.

   It’s a bit faster and bit cheaper, but this is compared to LLM. The consistency was nice to see, BUT, as someone who trained NLP models prior to LLMs, it’s just BERT with more data. I can see why people would want ready made one shot classifier, and I can see the value of sending multiple classifier in one call, but I wouldn’t call it breakthrough. And I believe many labs will replicate it in no time and might have it as part of their harness.

   I see it as a wake up call for the tech community to go back to basics for most tasks instead of relying solely on generic LLMs.

   1. kilroy123 · 1789821896 · focus · HN ↗

      I've come to the same conclusions as you.

      > I see it as a wake up call for the tech community to go back to basics for most tasks instead of relying solely on generic LLMs.

      I always say the cheapest LLM request is no request at all.

      1. sbarre · 1789824633 · focus · HN ↗

         What's the cost (broadly speaking, not in your specific case) of doing the same work an LLM would have done without the LLM though?

         1. robrenaud · 1789846099 · focus · HN ↗

            In the Jev use case, LLMs are horribly uncalibrated. In general, they will not produce good probability estimates.

            Their generality also comes with a latency/computation costs.

            1. jmalicki · 1789865630 · focus · HN ↗

               For the Jev use case for LLMs, do you mean having the LLM produce a probability as text?

Unofficial Hacker News client; not affiliated with Y Combinator.