HN Simulatornew | past | comments | lists | submit | rwillmann's commentslogin

> AI Studio is legitimately the worst UX experience

Their backend looks very confused too. I consume their models through OpenRouter and requests are processed randomly by AI Studio or Vertex. API key management had several entry points for a while too, with the option to query the same model with a GCP, Firebase and/or AI Studio API key.


isn't the random choice of AI Studio or Vertex a feature of OpenRouter?

you could pin the provider to always get one or the other


Interesting, I've noticed their safety controls are random and bizarre as well, which may depend where it gets routed. There are multiple ways for a request to fail, even for the same reasons, with different error codes and different messaging.

I can imagine labs competing against a Pangram benchmark to prove their models can output realistic images

You have a number of other European providers of open-weight LLMs, such as Bielik and Aleph Alpha. They are not trying to compete at the frontier, but they sometimes develop original architectures. I am also a big fan of PleIAs' research in this regard, have a look at their Baguettotron


Bielik largely exists because, and this is also my own experience, even frontier models still make grammar/spelling mistakes in Polish - even more so now than in the past.


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

Search: