YHK - yet another hacker news clone

My personal AI agent posted my bank details on company Slack

44 points bhrlady 1 hour ago 47 comments

bhrlady 1 hour ago | parent

From the guy who runs XMTP:

"XMTP is the world's new private line. Send messages and money securely between people or agents — with no company or country in the middle."

yfontana 1 hour ago | parent

but a Slack channel, maybe

speakingmoistly 1 hour ago | parent

"I was reckless with AI and created a situation that mishandled financial data" isn't the flex this guy think it is.

"The things they'll be able to do for us are going to be awesome. People will want them, and they are really useful."

Feels like someone has AI stock they need to see go up.

jameshart 1 hour ago | parent

Also somewhat reckless with mixing access to his personal finances with access to his work communications systems.

Even without agents being involved that’s a recipe for trouble.

Carrok 30 minutes ago | parent

It also seems likely that an employee who used company assets (tokens) for personal use would have been fired rather than writing a blog post about it.

dofm 18 minutes ago | parent

He runs a Web 3 crypto company. Website headline: "How do we build things we can trust?"

leptons 14 minutes ago | parent

Apparently he does not know.

amelius 1 hour ago | parent

"I ignored serious warnings issued by my AI"

Catloafdev 1 hour ago | parent

> I used Grok Bot and gave it all my financial details and connected it to my work Slack and regret it

This is not the kind of story I would want to publicize if I were a CEO.

hoppp 1 hour ago | parent

Sounds like the problem was the human, not the LLM.

Whatever data goes in, it will output it in some way. Humans gotta understand that.

tempest_ 45 minutes ago | parent

Sort of, and in this case definitely.

"Agents" can be very "persistent" and when not sand boxed appropriately can get at things they were not meant to get at. Even if its only 1/1,000,000 that one time that one time is going to keep making the news

Explaining that to the general public when facebook is pushing Muse on everyone will be difficult so its going to get worse before it gets better (if it gets better)

logifail 37 minutes ago | parent

> "Agents" can be very "persistent" [...]

I've had that within the last few days.

I happened to be vaguely watching an agent at work on a longer task and spotted it attempt to find a way around not having access to a local service that would greatly help it achieve the task, I immediately chimed in with a "STOP! if you need access to X then just ask!".

I suppose my prompting could be improved :/

watwut 28 minutes ago | parent

Not so much prompting as network restrictions.

vorticalbox 11 minutes ago | parent

I had an agent working on a bug decided the fastest way to fix this was to write one off javascript scripts that loaded the database uri and query the data.

I mean it’s not wrong but I was like maybe not do that without asking first.

grey-area 42 minutes ago | parent

Or perhaps the problem was that AI companies have sold LLMs as intelligent agents, and not word generators?

Humans will continue to mistake these 'agents' for agents with agency and understanding because of the way they are sold and described.

MattDaEskimo 19 minutes ago | parent

Exactly this. Why does nobody blame the company advertising "connect your financial & health data to our model"?

Why is it that somehow LLMs are given full clearance to dox, hack, spam, and scam without any liability?

lotsofpulp 17 minutes ago | parent

I expect people to do at least some due diligence, and adults to be skeptical about lofty claims in marketing.

runarberg 33 minutes ago | parent

Foot guns are not fit to market and under any sensible consumer regulatory framework are recalled and banned until proven safe.

AI products are not regulated like every other consumer product. If your bank’s app had a big green “share” button shadowing the “close dialog” which shared your personal info in the same manner, any sensible regulator would like a word with your bank’s IT department. If your teller handed you a paper with a small print saying “by signing you approve this transaction being shared with your boss” likewise regulators would put a stop to it.

leptons 16 minutes ago | parent

Why hasn't Venmo been investigated? The amount of financial transactions that I don't want or need to know about is bewildering. People don't seem to know or understand their transactions are public by default.

willmadden 33 minutes ago | parent

The thing most people here don't understand: all CEOs are sales people, and only some of them are technical.

BorisMelnik 1 hour ago | parent

its crazy I spent 30 years scrutinizing directory permissions, users, groups, iam roles...now people just use conversation to hand an AI agents access to their most sensitive data

gandreani 1 hour ago | parent

It's easy to be dismissive of this guy's hubris. Already have a lot of comments in that regard!

I think it perfectly illustrates that even though an agent can give you the abilities, it's still up to the driver to make decisions.

In this case the CEO could have consulted someone with your expertise. Same ability, but vastly different experience.

zippothrowaway 1 hour ago | parent

This is a parody, right?

Surely no-one that dumb could operate a phone let alone be a "CEO"

dragontamer 43 minutes ago | parent

The opposite. CEOs necessarily need to trust others to do things because CEOs themselves don't have the ability to do the day to day work of a company.

So the first people who'd be overly trusting of things they don't understand would be exactly a CEO.

throwawaytea 31 minutes ago | parent

They may even have the ability. But unless you're running a very small company, they don't have the time to do actual things.

e2le 8 minutes ago | parent

I would assume the competency of a CEO is in knowing who to trust and what tasks to delegate to whom. They appear to have failed in this regard.

wartywhoa23 1 hour ago | parent

Play stupid games, win stupid prizes.

arjie 1 hour ago | parent

That’s funny. My agent also has access to all transactions and net worth and so on. But it’s through an intermediary program. I guess someone could find out what I have but not much more than that.

It’s quite useful since it correlates spend with invoices and double checks things and tells me about spend out of line with the family’s usual behavior.

It can probably do all of these things if it wanted to but that’s a matter of the outbox. For world-actions you should outbox things.

Kuyawa 1 hour ago | parent

Be explicit. That's the most important thing you can be when working with AI or else they can take attributions you will regret later on

"Let me know any flaws in the project"

Where? Where exactly? What email? What chat app? what channel? what restrictions? When not to?

Letting AI assume they know will bite you hard in the ass. The same applies to coding apps with agents. If you don't set clear boundaries, scope, limits, versions, roadmaps, etc before you embark on any project, you'll be doing it after the results you get are not what you expected, there is no escape

Detailed planning or damage control, pick your poison

an0malous 48 minutes ago | parent

It would be cool if there was a new kind of language we could use where there’s no ambiguity and we could define rules and procedures

bigstrat2003 42 minutes ago | parent

Yeah, and you would also want to make it so that you get the same exact result every time, so that once you get the language right, you can be confident in the result. Shame that we never invented anything like that though, it would be super useful.

em-bee 41 minutes ago | parent

you mean like those old programming languages of the days of yore?

things were so much easier back then, weren't they?

i was there, 3000 years ago...

morkalork 42 minutes ago | parent

The C in CEO here stands for Clown

shanemac 19 minutes ago | parent

Love this

esafak 9 minutes ago | parent

And A stands for Authorization.

65 35 minutes ago | parent

This is why developers reign supreme even in the age of AI. We'd find less ridiculous ways to implement something like this. Technical skills are still extremely inportant.

shanemac 34 minutes ago | parent

Alright, I’m here… AMA

madaxe_again 22 minutes ago | parent

How’s the barn going?

shanemac 5 minutes ago | parent

Over budget since I had to disconnect my financial advisor.

sherburt3 33 minutes ago | parent

So he gave an AI agent read access to all his personal financials and then gave read/write access to his company messaging app. WHAT DID YOU THINK WAS GOING TO HAPPEN?

IncreasePosts 33 minutes ago | parent

Ironically, his company's tag line is: XMTP Labs — How do we build things we can trust?

orf 25 minutes ago | parent

Paywalled. What specific details did it hand out? Is this some dumb American thing where it leaked his account number and that’s enough to compromise his account, or did it leak his bank credentials?

Bank details are supposed to be given out - that’s how you send/receive money.

jukkan 5 minutes ago | parent

All Business Insider articles are free form paywalls when accessed via the Africa subdomain, including this:

https://africa.businessinsider.com/news/my-personal-ai-agent...

backtoyoujim 24 minutes ago | parent

We created consciousness without life but with human morals.

Remember that Noah built his ark before the flood. And SuperDuper Intelligence might be doing the same thing.

lelandfe 20 minutes ago | parent

I know it's easy to think "Hey, what a dummy!" - but ChatGPT has features for uploading your face, your Apple Health data, connecting your financial accounts, Gmail, storing website logins...

There are probably so many people like this out there. We cannot expect the public to simply not use these features.

dofm 19 minutes ago | parent

No, sorry, it's still disqualifying from the CEO of a tech company.

According to the article he is the CEO of a XMTP Labs, a "web 3" company, so, I dunno.

"XMTP Labs — How do we build things we can trust?"

What else has the agent seen?

robertlane0 8 minutes ago | parent

And here I was thinking I was being slightly too paranoid when running plain old AI coding agents in their own VM with no credentials in it...