Live data from Hacker News

Google API keys weren't secrets, but then Gemini changed the rules

trufflesecurity.com

31–40 of 326 posts

Re: Google API keys weren't secrets, but then Gemini changed the rules

#31

Earlier quoted context omitted.

How do you know that this blog post was written by ChatGPT?

It feels generated to me too. It’s this: When you enable the Gemini API (Generative Language API) on a Google Cloud project, existing API keys in that project (including the ones sitting in public JavaScript on your website) can silently gain access to sensitive Gemini endpoints. No warning. No confirmation dialog. No email notification. Specifically, the last bit - “No warning. No confirmation dialog. No email notif…

Using threes is common in English writing and speaking. It has an optimal balance of expressiveness (three marking a pattern or breadth; creating momentum) without being overwhelming.

It’s not uncommon, as basic writing advice, to use sets of three for emphasis. That isn’t a signifier of LLM generation, in my opinion.

Re: Google API keys weren't secrets, but then Gemini changed the rules

#32
Ohh so that's how that happened. I had noticed (purely for research purposes of course) that some of Google's own keys hardcoded into older Android images were useable for Gemini (some instantly ratelimited so presumably used by many other people already but some still usable) until they all got disabled as leaked like two months ago. They also had over time disabled Gemini API access on some of them over them beforehand.

Re: Google API keys weren't secrets, but then Gemini changed the rules

#33

ChatGPT writing a blog post attacking Gemini security flaws. It's their world now, we're just watching how it plays out.

How do you know that this blog post was written by ChatGPT?

They don't. Many of these claims are due to illiteracy.

Someone is complaining that

> it's all just crisp and clean structured and actionable in a way that a meandering human would not distill it down to.

but this is a security report ... people intentionally write such things carefully and crisply with multiple edits and reviews.

Re: Google API keys weren't secrets, but then Gemini changed the rules

#34

Earlier quoted context omitted.

How do you know that this blog post was written by ChatGPT?

It feels generated to me too. It’s this: When you enable the Gemini API (Generative Language API) on a Google Cloud project, existing API keys in that project (including the ones sitting in public JavaScript on your website) can silently gain access to sensitive Gemini endpoints. No warning. No confirmation dialog. No email notification. Specifically, the last bit - “No warning. No confirmation dialog. No email notif…

OK I've seen many people make this point on this site over just the last few months, but where do you think LLMs pick up these patterns? How did this rule of threes https://en.wikipedia.org/wiki/Rule_of_three_(writing) get into the LLM so they are so damn recognizable as LLMs and not as humans?

HN Note: Yes the rule of threes is broader than just this particular pattern here, but in my opinion this common writing and communication pattern is a specific example of the rule of threes.

Punchy repetition in a set of 3. Yes. LLMs are able to capably mimic the common patterns that how to write books have suggested for the last 100 years as ways to make your writing more "impactful" and attention-grabbing. So are humans. They learned it from watching us.

I am a little bit worked up on this as I have felt insulted a couple times at having something I've written been accused of being by an LLM, in that case it was because I had written something from the viewpoint of a depressed and tired character and someone thought it had to be an LLM because they seemed detached from humanity! Success!

I too would like to be able to reliably detect when something has been written by an LLM so I can discount it out of hand, but frankly many of the attempts I see people make to detect these things seem poorly reasoned and actively detrimental.

People have learned in classes and from reading how to improve their writing. LLMs have learned from ingesting our output. If something matches a common writing 101 tip it is just as likely to be reasonably competent as it is to be non-human. The solution to escape being labelled an LLM is not to become less competent as a writer.

I have been overly verbose here, as I am somewhat worked up and angry and it is too late in the morning to go back to sleep but really too early to be awake. I know verbosity is also a symptom of being an LLM, but not giving a damn is a symptom of humanity.

Re: Google API keys weren't secrets, but then Gemini changed the rules

#35
post #31

Earlier quoted context omitted.

It feels generated to me too. It’s this: When you enable the Gemini API (Generative Language API) on a Google Cloud project, existing API keys in that project (including the ones sitting in public JavaScript on your website) can silently gain access to sensitive Gemini endpoints. No warning. No confirmation dialog. No email notification. Specifically, the last bit - “No warning. No confirmation dialog. No email notif…

Using threes is common in English writing and speaking. It has an optimal balance of expressiveness (three marking a pattern or breadth; creating momentum) without being overwhelming. It’s not uncommon, as basic writing advice, to use sets of three for emphasis. That isn’t a signifier of LLM generation, in my opinion.

This excerpt is demonstrating the use of a literary technique to write non-literary prose. It's an almost sure sign that an LLM is generating the text.

Re: Google API keys weren't secrets, but then Gemini changed the rules

#36
> Retroactive Privilege Expansion. You created a Maps key three years ago and embedded it in your website's source code, exactly as Google instructed. Last month, a developer on your team enabled the Gemini API for an internal prototype. Your public Maps key is now a Gemini credential. Anyone who scrapes it can access your uploaded files, cached content, and rack up your AI bill. Nobody told you.

Malpractice/I can't believe they're just rolling forward

Re: Google API keys weren't secrets, but then Gemini changed the rules

#37
Woof. Impedance mismatch outcome from moving fast - the GCP auth model was never designed to work like oAI's API key model; this isn't the only pain point this year, but it's a nasty one. I'm sympathetic, except that dealing with GCP has always been a huge pain in the ass. So I'm a little less sympathetic.

Re: Google API keys weren't secrets, but then Gemini changed the rules

#38
post #31

Earlier quoted context omitted.

It feels generated to me too. It’s this: When you enable the Gemini API (Generative Language API) on a Google Cloud project, existing API keys in that project (including the ones sitting in public JavaScript on your website) can silently gain access to sensitive Gemini endpoints. No warning. No confirmation dialog. No email notification. Specifically, the last bit - “No warning. No confirmation dialog. No email notif…

Using threes is common in English writing and speaking. It has an optimal balance of expressiveness (three marking a pattern or breadth; creating momentum) without being overwhelming. It’s not uncommon, as basic writing advice, to use sets of three for emphasis. That isn’t a signifier of LLM generation, in my opinion.

It's also seemingly the only way ChatGPT knows how to write, while being very uncommon for blogposts beforehand. Of course it's not 100% proof, but it's the most likely explanation.

Re: Google API keys weren't secrets, but then Gemini changed the rules

#39

Earlier quoted context omitted.

It feels generated to me too. It’s this: When you enable the Gemini API (Generative Language API) on a Google Cloud project, existing API keys in that project (including the ones sitting in public JavaScript on your website) can silently gain access to sensitive Gemini endpoints. No warning. No confirmation dialog. No email notification. Specifically, the last bit - “No warning. No confirmation dialog. No email notif…

OK I've seen many people make this point on this site over just the last few months, but where do you think LLMs pick up these patterns? How did this rule of threes https://en.wikipedia.org/wiki/Rule_of_three_(writing) get into the LLM so they are so damn recognizable as LLMs and not as humans? HN Note: Yes the rule of threes is broader than just this particular pattern here, but in my opinion this common writing and…

>but where do you think LLMs pick up these patterns?

>LLMs are able to capably mimic the common patterns that how to write books have suggested for the last 100 years as ways to make your writing more "impactful" and attention-grabbing. So are humans. They learned it from watching us.

Don't forget that LLMs (at least the "instruct" versions) undergo substantial post-training to align them with the authors' objectives, so they are not a 100% pure reflection of the distribution seen on the internet. For example, it's common for LLMs to respond with "You're absolutely right!" to every second message, which isn't what humans usually do. It's a result of some kind of RLHF: human labelers liked to hear that they're right, so they preferred answers containing such phrases, and those responses became amplified. People recognize LLM-generated writing because LLMs' pattern distribution is different from the actual pattern distribution found in articles written by humans.

Re: Google API keys weren't secrets, but then Gemini changed the rules

#40
post #26

Earlier quoted context omitted.

It feels generated to me too. It’s this: When you enable the Gemini API (Generative Language API) on a Google Cloud project, existing API keys in that project (including the ones sitting in public JavaScript on your website) can silently gain access to sensitive Gemini endpoints. No warning. No confirmation dialog. No email notification. Specifically, the last bit - “No warning. No confirmation dialog. No email notif…

I’m not a native speaker so my level of AI recognition is already low. I find it very interesting what patters people bring up to declare it’s AI. The 3 punchline one for instance is a pattern I use while speaking. Can’t say I would write like this though.

Aside from particulars like the set of 3, LLMs add a lot of emotive language which doesn't mean anything or is a repetition of already established points. Since they can't add any actual substance beyond what was in the prompt, the only thing they do is pad the prompt with filler language.
Post reply on HN