Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I mostly use LLMs as a more convenient Google and to automate annoying code transformations with a conveniency of a natural language interface. Sometimes, I use it to "improve" my writing style.

I have to admit I was a bit surprised how bad LLMs are at the continue this essay task. When I read it in the blog I suspected this might have been a problem with the prompt or the using one of the smaller variants of Gemini. So I tried it with Gemini 2.5 Pro and iterated quite a bit providing generic feedback without offering solutions. I could not get the model to form a coherent well reasoned argument. Maybe I need to recalibrate my expectations of what LLMs are capable, but I also suspect that current models have heavy guardrails, use a low temperature and have been specifically tuned for problem solving and avoid hallucinations as much as possible.



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: