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

If you want to try it out via their API you can run it through my LLM tool using uvx like this:

  uvx --with 'https://github.com/simonw/llm/archive/801b08bf40788c09aed6175252876310312fe667.zip' \
    llm -m gpt-4.5-preview 'impress me'
You may need to set an API key first, either with `export OPENAI_API_KEY='xxx'` or using this command to save it to a file:

  uvx llm keys set openai
  # paste key here
Or this to get a chat session going:

  uvx --with 'https://github.com/simonw/llm/archive/801b08bf40788c09aed6175252876310312fe667.zip' \
    llm chat -m gpt-4.5-preview

I'll probably have a proper release out later today. Details here: https://github.com/simonw/llm/issues/795


Just curious, does this stream the output or renders all at once ?


It streams the output. See animated demo here (bottom image on the page) https://simonwillison.net/2025/Feb/27/introducing-gpt-45/




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

Search: