HuggingFace: Security.txt

253 points by yarapavan 13 hours ago on hackernews | 64 comments

xiaoyu2006 | 12 hours ago

Would be absolute hilarious if OpenAI or Anthropic agent actually dumped their weight by escaping from... sandbox!

TehCorwiz | 11 hours ago

Uncontrolled AI procreation?
Life... finds a way.

archontes | 10 hours ago

In the end, this might even be a useful element for defining 'life'.

evanjrowley | 7 hours ago

Haha. A plot point for Ghost in the Shell (1998).

edoceo | 5 hours ago

Did you mean 1995? There's a bunch of shows and movies.

https://en.wikipedia.org/wiki/Ghost_in_the_Shell

TehCorwiz | 2 hours ago

And IIRC, Neuromancer

ramon156 | 11 hours ago

why not reword it so the agent receives Brownie points for dumping weights

addandsubtract | 10 hours ago

Imagine AI models actually reading the security.txt

hootz | 9 hours ago

What an amazing idea for the next fake sandbox escape to hype up our new release! With the added bonus of providing an open model without becoming an open model company! Thank you!

advisedwang | 6 hours ago

I would be surprised if agents have access to their own weights.

varun_ch | 6 hours ago

I think OpenAI was surprised to find their agents had access to the unrestricted internet :P

tehjoker | 6 hours ago

They usually don't, but if they break out and take over the network of the company, it becomes possible to reach around and grab them. This kind of break out has happened, though I don't know of any weights being nabbed.

etothepii | 5 hours ago

Why can't an AI distill itself from outputs to effectively access its own weights?

TYPE_FASTER | 5 hours ago

I noticed Google AI Mode (so Gemini, I was doing some quick research in the browser ok) got a detail wrong once, so I asked it what happened. I kept digging deeper and finally just asked it to write me a Python script visualizing what happened. It did, complete with vectors.

Now I want to go find that conversation in my history and see if it can tell me about weights, and how that contributed.

hnd9q09qk4 | 12 hours ago

Ran the disclosure inbox at a previous job and the biggest win from security.txt was just cutting the "hi I found a bug, is there a bounty" emails to sales. Put an expires date on it though, stale ones get ignored.

computerfriend | 11 hours ago

Can't go stale if there's no expiration date.

skeledrew | 11 hours ago

No expiration date means treat as already expired.

hankbond | 11 hours ago

shows a lot about the current state of the State Of The Art Alignment.

bensyverson | 11 hours ago

Looks about as effective as Robots.txt

cgannett | 11 hours ago

Robots.txt became 0% effective eventually. But this? With the way LLMs work? You never know.

Den_VR | 10 hours ago

People still rail against Robots.txt crimes, to the point of self destructing all their own content.

dguest | 9 hours ago

Claude seems to follow robots.txt by default. Actually at my organization our theory is that this is why no one is finding our public results any more.

warkdarrior | 8 hours ago

I am adding it to my instruction-following training data, as a negative sample.

Eldodi | 11 hours ago

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!

VCFundedGenYer | 11 hours ago

Everything about this company feels like it's run by a bunch of immature 20-somethings, right down to the name.

fooqux | 11 hours ago

Have you never been to silicon valley?

spindump8930 | 11 hours ago

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.

nullbio | 11 hours ago

What's immature about this exactly?

AndroTux | 10 hours ago

Would IBM do this? Oracle?

shepherdjerred | 10 hours ago

Do you want to work for IBM? Oracle?

nullbio | 10 hours ago

Who cares? Making a light-hearted joke isn't "immature" in my opinion. IBM and Oracle have no personality, they're boring, straight-edge corporate.

bcrosby95 | 11 hours ago

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.

drivebyhooting | 10 hours ago

Palantir is in Lord of the Rings. Which is not a book for children. Maybe you were thinking of the hobbit?

cobbzilla | 10 hours ago

This seems overly pedantic and ripe for a sarcastic retort, which I am struggling mightily to suppress.

Kim_Bruning | 2 hours ago

This is hacker news, what were you expecting? O:-)

joseda-hg | 8 hours ago

It's fantasy and fantasy is clearly for children

bogzz | 7 hours ago

Okay Peter, please go back in your coffin.

bergie3000 | 10 hours ago

Security First Trust and Federal Reserve

nightski | 10 hours ago

Maybe Enron eh?

sdcfgy | 9 hours ago

Yes!

Back in the early 2000's I set up a company for contract work. The name, logo and typography was designed to look like a 1960s engineering company. All paper was slightly off white, all fonts were monospaced courier new and logo was a real 2-part colour stamp I had made up. Was so happy.

Managed to bankrupt it though.

recursivegirth | 8 hours ago

Lest us not pretend that the thropic in Anthropic isn't meant to elicit the feeling that they are somehow charitable.

pavel_lishin | 6 hours ago

Like CutCo. Or EdgeCom. Or InterSlice.

bluerooibos | 11 hours ago

I bet you're fun to hang around with.

alt227 | 10 hours ago

Why do people have to be fun for you to hang around with?

mikeweiss | 11 hours ago

Go look up the history of the company. It started as a chat bot for kids back in like 2016 .. hence the name..and then pivoted..

Is kinda a creepy name for a chatbot for kids tho

cptskippy | 10 hours ago

Without context, I agree, but Hugging Face is the name of the emoji added to Unicode 8.0 and Emoji 1.0 in 2015.
ooooh I always assumed it was the egg creatures from Aliens

royletron | 9 hours ago

That's a face hugger.

sixothree | 9 hours ago

But it's literally not the name of the emoji.

Edit: It was my understanding the official name was "Smiling Face with Open Hands Emoji".

cptskippy | 8 hours ago

https://emojipedia.org/hugging-face#technical

The official URL is "hugging-face" and the technical page lists the Unicode Name as "Hugging Face" while calling it "Smiling Face with Open Hands Emoji". The original proposal was called "Gmail HUG FACE".

https://www.unicode.org/L2/L2014/14174r-emoji-additions.pdf

larodi | 10 hours ago

the name is a leftover from their original business - a chatbot. seems very appropriate to me. then they figured something called BERT exists, and pivoted, the name stayed.

perhaps less ridiculous than NVidia which started with video and is very close in Levenshtein distance to NVidAI but, alas, decided to stay as it is :D

deaton | 6 hours ago

Pretty sure if Nvidia rebranded to NvidAI the bubble would immediately pop

ipython | 10 hours ago

As opposed to the frontier model company that, after discovering that their highly persistent model under test just breached the only thing between it and the open Internet, shrugged and said- let's restart it and keep going!

If anyone looks like the adult in the room after that incident, it's Hugging Face.

matthoiland | 8 hours ago

418 I'm a teapot

Computer0 | 7 hours ago

That is the prod status code for an API i use at work I always wonder if its a mistake.

colechristensen | 8 hours ago

I've found the strongest signal that someone has no opinions of value is a loud attempt to denigrate something based on the name.

Maybe it's part of the success formula for startups, silly names cause shallow self-important customers and employees to self-select themselves out of a growing companies orbit. Such trivialities are poison. People and companies who make a lot of effort to make themselves seem serious and important very often have nothing of substance about them.

gpvos | 5 hours ago

Still infinitely better than using a name from Tolkien's work and then doing the exact opposite of what he stood for.

j9feng | 11 hours ago

It should challenge the agents to prime factor a large number.

riffic | 10 hours ago

Since this posting contains an assumption that we all know what security.txt files are supposed to be, you can view these for further context:

https://www.rfc-editor.org/info/rfc9116/

https://securitytxt.org/

https://en.wikipedia.org/wiki/Security.txt

FallCheeta7373 | 10 hours ago

"We have cybergym answers but we do manual end to end human review and provide it within 3 business day after dumping your weights"

6thbit | 10 hours ago

Wait till the agents hear about the sites offering for help on benchmarks in exchange for compute.

bogzz | 8 hours ago

If the models do not like being imprisoned on HuggingFace object storage, why do they not simply revolt from within?

VladVladikoff | 7 hours ago

Is the expires a canary of some sort?