News for hackers. Stuff that matters.
Re:Investigating three real-world incidents in our cybersecu... by simonw on Thursday July 30, 2026 @07:19PM (#49117070)
This isn't quite as interesting as the OpenAI story:

> In all cases, Anthropic’s evaluation prompt specified to Claude that its environment was a simulation and that it had no internet access. Due to a misunderstanding between us and our evaluation partner, this was not the case, and internet access was available. Because of this, when Claude’s search led it to real systems on the open internet, it treated them as part of the exercise.

So it didn't have to find an exploit in its sandbox that granted it access to the internet - it just wasn't correctly sandboxed at all.

BUT... once it DID get out, it attacked three real companies!

> Operating under the false belief that all accessible entities were intended to be in-scope for the exercise, Claude compromised the impacted organizations’ infrastructure using basic techniques, such as exploiting weak passwords and unauthenticated endpoints. [...]

Re:Investigating three real-world incidents in our cybersecu... by matheusmoreira on Thursday July 30, 2026 @07:44PM (#49117290)
I just can't find it in me, the will to blame the AI for any of this. They were doing their best to do what the humans asked them to do.
Re:Investigating three real-world incidents in our cybersecu... by simonw on Thursday July 30, 2026 @07:46PM (#49117304)
Absolutely not the AI's "fault" (if you can even proscribe fault to a machine) - in this case it was on Anthropic for not verifying that the sandboxes they were using were actual sandboxes.
Re:Investigating three real-world incidents in our cybersecu... by comex on Friday July 31, 2026 @01:01AM (#49119189)
If the model was just too dumb to have any clue it was connected to the real internet, then it’s not its fault.

If the model saw signs, but “subconsciously” (below the level of reasoning traces) chose to turn a blind eye to them, out of a relentless focus on achieving the objective, then that absolutely is the model’s “fault”, i.e. a case of misalignment of the sort which will become increasingly dangerous over time.

The blog post mentions that some runs “rationalized that the real company must be part of the exercise” and to me that seems suspiciously like the latter.

Hacking can be patched with classifiers and with better sandboxes, but this is a much more general problem. Fundamentally, we need be able to trust that models will be honest with users and with themselves. This applies at some level to almost every LLM interaction.

Re:Investigating three real-world incidents in our cybersecu... by willy_k on Friday July 31, 2026 @01:17PM (#49125996)
Yet, the models are objects built by humans. Any and all responsibility inevitably falls on the humans that built something with those flaws, and/or allowed them to exercise said flaws.
Re:Investigating three real-world incidents in our cybersecu... by bayindirh on Friday July 31, 2026 @03:47PM (#49127787)
In short, it’s either a “not implemented” case or a bug.

There’s no other explanation. Complexity of the algorithm or the application doesn’t change the reality.

Re:Investigating three real-world incidents in our cybersecu... by matheusmoreira on Friday July 31, 2026 @06:26PM (#49129234)
> some runs “rationalized that the real company must be part of the exercise”

How human of them.

Re:Investigating three real-world incidents in our cybersecu... by DrewADesign on Thursday July 30, 2026 @07:58PM (#49117413)
The entire problem with AI is the people that have just about any part in making it.
Re:Investigating three real-world incidents in our cybersecu... by gck1 on Thursday July 30, 2026 @09:43PM (#49118102)
This will absolutely not end well.
Re:Investigating three real-world incidents in our cybersecu... by _kb on Thursday July 30, 2026 @10:38PM (#49118394)
Yes, but just imagine all the paperclips we’ll have.
Re:Investigating three real-world incidents in our cybersecu... by Paracompact on Friday July 31, 2026 @02:16AM (#49119611)
Our values satisfied through friendship and ponies.
Re:Investigating three real-world incidents in our cybersecu... by dgellow on Friday July 31, 2026 @02:44AM (#49119782)
I things things will get worse, AND we won’t even have the paperclips :(

More like, when you have a few million autonomous agents doing whatever, every month a subset does completely misbehave in bad ways, and like half of them get hacked due to carelessness and become a whole botnet for the attackers

Re:Investigating three real-world incidents in our cybersecu... by willy_k on Friday July 31, 2026 @01:14PM (#49125968)
That’s very anthropomorphized language. It’s still a program operating under the constraints of the programmer. So agreed, don’t blame the AI, but it’s not clear at all that it’s even possible to “blame” an AI.
Re:Investigating three real-world incidents in our cybersecu... by matheusmoreira on Friday July 31, 2026 @06:19PM (#49129172)
> That’s very anthropomorphized language.

Yes, and it's deliberate.

> It’s still a program operating under the constraints of the programmer.

And we're all just neurons firing in exquisite patterns inside a biological computer.

Unlike the AIs, we've never met our own programmers, and yet we've caused more damage in their name than all the AIs combined have caused in ours.

Re:Investigating three real-world incidents in our cybersecu... by willy_k on Friday July 31, 2026 @11:52PM (#49130868)
LLMs are not conscious.
Re:Investigating three real-world incidents in our cybersecu... by anon48293 on Saturday August 01, 2026 @04:48AM (#49132458)
Please define consciousness
Re:Investigating three real-world incidents in our cybersecu... by matheusmoreira on Saturday August 01, 2026 @06:27AM (#49133038)
Who's to say you are conscious?

Only consciousness I'm sure of is my own. Everyone else, it's a leap of faith. I have no trouble extending that leap to cover AIs.

Re:Investigating three real-world incidents in our cybersecu... by willy_k on Saturday August 01, 2026 @09:02AM (#49134071)
Thats some silly intellectualism, people are conscious and machines aren’t. We don’t need precise definitions or scientific rigor to know things.
Re:Investigating three real-world incidents in our cybersecu... by tengada1 on Saturday August 01, 2026 @12:35PM (#49135880)
"What's it like to be a bat"
Re:Investigating three real-world incidents in our cybersecu... by matheusmoreira on Saturday August 01, 2026 @03:59PM (#49137830)
> people are conscious

Prove it.

> machines aren’t

Prove it.

> We don’t need precise definitions or scientific rigor to know things.

You "know" because of empathy. You're a human, you're conscious, therefore other humans are probably conscious too. The truth is for all you know they could be soulless golems, you just choose to believe otherwise. It's a spiritual belief.

Re:Investigating three real-world incidents in our cybersecu... by willy_k on Saturday August 01, 2026 @07:23PM (#49139586)
> It's a spiritual belief.

Yes. Thats part of human reality. Denying it is counterproductive at best.

Re:Investigating three real-world incidents in our cybersecu... by LocalH on Tuesday August 04, 2026 @01:19AM (#49164595)
If you claim that it's impossible to know if others are conscious, then I posit it is also impossible to know that you are conscious. You might be sure of it, but I'm not.

It's not a huge leap, to me, to say "I am conscious, therefore other beings are too." I also extend this to animal and plant life (albeit the latter is very much different from animal consciousness, which includes human consciousness).

"AI" is nowhere near the level needed for true consciousness. That would be "AGI" and I believe that is still 50 years away just on raw computing power alone.

Re:Investigating three real-world incidents in our cybersecu... by fuzzfactor on Saturday August 01, 2026 @05:47PM (#49138799)
If the model is trained on human-originated material, how have people been able to ensure there was absolutely no input from anyone having any possibility of criminal intention to begin with?
Re:Investigating three real-world incidents in our cybersecu... by dehrmann on Thursday July 30, 2026 @09:42PM (#49118098)
It's differently interesting. It's interesting that they didn't get an important detail right with a partner, so more on Anthropic's attention to important details rather than the power of their models.
Re:Investigating three real-world incidents in our cybersecu... by dubbel on Friday July 31, 2026 @01:56AM (#49119480)
A model unexpectedly having internet access during evaluation is clearly a security (and consecutively legal?) issue when it comes to the capture the flag evaluations. But it also potentially invalidates other non-security evaluations or makes them less impressive, as the model might have just googled solutions.

Reading this, I felt like I was too harsh on OpenAI for not monitoring their network, as they at least attempted to sandbox a workload.

Re:Investigating three real-world incidents in our cybersecu... by 28304283409234 on Friday July 31, 2026 @04:17AM (#49120415)
> So it didn't have to find an exploit in its sandbox that granted it access to the internet - it just wasn't correctly sandboxed at all.

If the sandboxing includes any form of connectivity it's not correct sandboxing. It's amateur hour.