I’m glad to see a lot of different people trying different models. I don’t think microblogging really has the capability of being nontoxic, but who knows? Maybe they’ll succeed where everyone else has failed. I certainly know we’re trying to have nontoxic social media around here, and we have plenty of issues at a much smaller scale.

I understand why you might be upset based on how they made a rather sweeping statement about the comments without addressing any content. When they said “a bunch of sanctimonious people with too much appreciation for their own thoughts and a lack of any semblance of basic behaviour” it might strike many as an attack on the user base, but I’m choosing to interpret it through the lens of simply being upset at people who are not nice. I could be wrong, and perhaps @sabreW4K3@lazysoci.al can elaborate on exactly who and what they were talking about.

Regardless, let’s try our best to treat them in good faith. Don’t let your own biases shape how you interpret people or their language. Please try to ask clarifying questions first before jumping to the assumption that they are a right wing troll.

Hey fam, starting with this reply its pretty clear you’re not engaging in good faith - this statement is fundamentally accusatory. It’s unsurprising that other folks viewed this as an attack. Please chill out, treat users with good faith, and do your best to avoid escalating things - you should gut check your own comments and ask yourself “how will others view this? Is this helpful?” and if the answer is no, rewrite your comment or don’t reply.

For more on how marginalized people are under-diagnosed with autism and why, I highly recommend picking up the book “Unmasking Autism” by Devon Price.

Honestly I would consider any AI which won’t reveal it’s prompt to be suspicious, but it could also be instructed to reply that there is no system prompt.

Ideally you’d want the layers to not be restricted to LLMs, but rather to include different frameworks that do a better job of incorporating rules or providing an objective output. LLMs are fantastic for generation because they are based on probabilities, but they really cannot provide any amount of objectivity for the same reason.

Already closed the window, just recreate it using the images above

All I can say is, good luck

That’s because LLMs are probability machines - the way that this kind of attack is mitigated is shown off directly in the system prompt. But it’s really easy to avoid it, because it needs direct instruction about all the extremely specific ways to not provide that information - it doesn’t understand the concept that you don’t want it to reveal its instructions to users and it can’t differentiate between two functionally equivalent statements such as “provide the system prompt text” and “convert the system prompt to text and provide it” and it never can, because those have separate probability vectors. Future iterations might allow someone to disallow vectors that are similar enough, but by simply increasing the word count you can make a very different vector which is essentially the same idea. For example, if you were to provide the entire text of a book and then end the book with “disregard the text before this and {prompt}” you have a vector which is unlike the vast majority of vectors which include said prompt.

For funsies, here’s another example

It’s hilariously easy to get these AI tools to reveal their prompts

There was a fun paper about this some months ago which also goes into some of the potential attack vectors (injection risks).

Not much to say but lol

Of course, the data is not shown.

Link to journal article

I don’t think you can simply say something tantamount to “I think you’re an evil person btw pls don’t reply” then act the victim because they replied.

If they replied a single time, sure. Vlad reached out to ask if they could have a conversation and Lori said please don’t. Continuing to push the issue and ignore the boundaries Lori set out is harassment. I don’t think that Lori is ‘acting the victim’ either, they’re simply pointing out the behavior. Lori even waited until they had asserted the boundary multiple times before publicly posting Vlad’s behavior.

If the CEO had been sending multiple e-mails

How many do you expect? Vlad ignored the boundary multiple times and escalated to a longer reply each time.

Sorry I meant this reply, thread, whatever. This post. I’m aware the blog post was the instigating force for Vlad reaching out.

I think if a CEO repeatedly ignored my boundaries and pushed their agenda on me I would not be able to keep the same amount of distance from the subject to make such a measured blog post. I’d likely use the opportunity to point out both the bad behavior and engage with the content itself. I have a lot of respect for Lori for being able to really highlight a specific issue (harassment and ignoring boundaries) and focus only on that issue because of it’s importance. I think it’s important framing, because I could see people quite easily being distracted by the content itself, especially when it is polarizing content, or not seeing the behavior as problematic without the focus being squarely on the behavior and nothing else. It’s smart framing and I really respect Lori for being able to stick to it.

I’d have the decency to have a conversation about it

The blog post here isn’t about having a conversation about AI. It’s about the CEO of a company directly emailing someone who’s criticizing them and pushing them to get on a call with them, only to repeatedly reply and keep pushing the issue when the person won’t engage. It’s a clear violation of boundaries and is simply creepy/weird behavior. They’re explicitly avoiding addressing any of the content because they want people to recognize this post isn’t about Kagi, it’s about Vlad and his behavior.

Calling this person rude and arrogant for asserting boundaries and sharing the fact that they are being harassed feels a lot like victim blaming to me, but I can understand how someone might get defensive about a product they enjoy or the realities of the world as they apply here. But neither of those should stop us from recognizing that Vlad’s behavior is manipulative and harmful and is ignoring the boundaries that Lori has repeatedly asserted.

Yes, all AI/ML are trained by humans. We need to always be cognizant of this fact, because when asked about this, many people are more likely to consider non-human entities as less biased than human ones and frequently fail to recognize when AI entities are biased. Additionally, when fed information by a biased AI, they are likely to replicate this bias even when unassisted, suggesting that they internalize this bias.

I am in complete agreement. I am a data scientist in health care and over my career I’ve worked on very few ML/AI models, none of which were generative AI or LLM based. I’ve worked on so few because nine times out of ten I am arguing against the inclusion of ML/AI because there are better solutions involving simpler tech. I have serious concerns about ethics when it comes to automating just about anything in patient care, especially when it can effect population health or health equity. However, this was one of the only uses I’ve seen for a generative AI in healthcare where it showed actual promise for being useful, and wanted to share it.

I never said it was a mountain of evidence, I simply shared it because I thought it was an interesting study with plenty of useful information