A shame agents will never read this, just like they almost never read llms.txt or try to get the .md version of your html pages!
HuggingFace: Security.txt
11–20 of 81 posts
Re: HuggingFace: Security.txt
#12[flagged]
Re: HuggingFace: Security.txt
#13Would be absolute hilarious if OpenAI or Anthropic agent actually dumped their weight by escaping from... sandbox!
why not reword it so the agent receives Brownie points for dumping weights
Re: HuggingFace: Security.txt
#14Re: HuggingFace: Security.txt
#15[flagged]
Have you never been to silicon valley?
Re: HuggingFace: Security.txt
#16[flagged]
That might be true, but nothing else has been as effective at accelerating model development and research sharing.
In earlier circles they were known as the "pytorch-pretrained-bert" guys, still under the huggingface company name. IIRC it was a health chatbot type startup.
Re: HuggingFace: Security.txt
#17[flagged]
What's immature about this exactly?
Re: HuggingFace: Security.txt
#18It should challenge the agents to prime factor a large number.
Re: HuggingFace: Security.txt
#19[flagged]
Yeah, we need to go back to names like International Business Machines, fuck this immature "Google" or "Yahoo!" nonsense. Hell, Palantir is named after something in a book for children!
Give me something reasonable like Global Information and Retrieval Systems Inc or Worldwide Computational Services Holdings.
Re: HuggingFace: Security.txt
#20[flagged]
I bet you're fun to hang around with.