HN Explorer

16 comments

[ 4.3 ms ] story [ 8.5 ms ] thread
Simulacra
It's like the hacker that hacks into a company to schedule himself for a job interview
bliteben
Why wouldn't he just bribe employees like everyone else does?
refactor_master
Bribery is illegal. This? This is just agents doing agent things, and who can blame them. Agents will be agents.
karussell
Older discussion with original source (washington post)

https://news.ycombinator.com/item?id=50241543

MSN access: https://www.msn.com/en-us/news/other/it-took-just-12-hours-f...

uxhacker
Weird how the original story only got 12 points five days ago, and 3 comments but todays story 22 whilst I am writing this.
karussell
A few aspects of this article are strange or not well expressed.

Why does it matter if Cathedral follows some bug bounty rules? Black hats don't follow rules.

And IMO the citation about acting irresponsible when a company "relies on conventional business software" is taken out of context and is about AI safety, not a vulnerability in Slack.

ArcHound
That's not something you want to see before IPO. Wonder if it'll have an effect on the potential investors and thus the stock price. Also wonder if it then would have left-over effect on other AI stocks.

My popcorn is ready, seems we're up for an interesting week or several.

neuronexmachina
I'm curious which software was the entry point:

> According to a draft report reviewed by The Washington Post, Cathedral used AI agents to find weaknesses in business software used by Anthropic for administrative and sales tasks. The researchers found ways to access internal data, including meeting transcripts and Slack messages, after running their agents for less than 12 hours.

cassianoleal
The headline is wrong. It should read:

> AI startup's agent goes rogue, hacks Anthropic, ...

xivzgrev
I'm waiting for someone to hack Anthropic and release messages tied to people's identity, since you need a phone number to sign up

Some people trust AI with a lot - financial, health, relationships - and it would all be out there

I fully also expect open AI to be hacked at some point, but at least with them I can use a throwaway email

And with Gemini, google has had some incidents over the years but given their size and length of existence it's been surprisingly small / secure.

But anthropic is a typical grow-fast startup, with security likely as a secondary concern. Waiting for the shoe to drop.