Re:73% of AI startups are just prompt engineering
by cess11 on Sunday November 23, 2025 @12:34PM
(#46025433)
"I found 12 companies that left API keys in their frontend code. I reported them all. None responded."
They claim to have found that.
Re:73% of AI startups are just prompt engineering
by hn_throwaway_99 on Sunday November 23, 2025 @12:56PM
(#46025735)
> It sounds like some of these companies call the OpenAI or Anthropic APIs directly from their frontend.
Which would be a major security hole. And sure, lots of startups have major security holes, but not enough that he could come up with these BS statistics.
I'm a little dismayed at how high up this has been voted given the data is guaranteed to be made up.
Re:73% of AI startups are just prompt engineering
by kllrnohj on Sunday November 23, 2025 @02:42PM
(#46026623)
> > It sounds like some of these companies call the OpenAI or Anthropic APIs directly from their frontend.
> Which would be a major security hole.
An officially supported security hole
https://platform.openai.com/docs/api-reference/realtime-sess...
But I'd like to know an actual answer to this, too, especially since large parts of this post read as if they were written by an LLM.