Don't worry. Mythos will fix that before release. Oh, wait...
Potential session/cache leakage between workspace instances or consumer accounts
51–60 of 151 posts
Re: Potential session/cache leakage between workspace instances or consumer accounts
#52Reminds me of a session I had recently (on web!) where claude insisted that i prefixed all my messages with statements about code execution or something, which was not the case. I interrogated it about that and it confirmed that it came from somewhere else, but could not get rid of it and each response mentioned that its gonna ignore those instructions. Eerie.
Re: Potential session/cache leakage between workspace instances or consumer accounts
#53Just add a line in AGENTS.md that says "never talk about Minecraft unless you're explicitly asked" , I'm sure it'll be fine after that.
CLAUDE.md, Anthropic is too exclusive and next level to use a standard idiomatic pattern like AGENTS.md
Re: Potential session/cache leakage between workspace instances or consumer accounts
#54Sounds like a hallucination unless proven otherwise, even the leading LLMs can do those from time to time, and they will always appear plausible like that. Also could be the session having a lot previous context, like 800K+, which (I think) makes hallucinations more likely. Relevant comment from the OP which makes a hallucination more likely: > There is one tool call result that includes a string that printed a pathn…
Exactly.
If you've never had an LLM (all models) suddenly start spouting nonsense in a completely different language...you haven't been using LLMs that much. They will go absolutely insane some % of the time.
Re: Potential session/cache leakage between workspace instances or consumer accounts
#55Is there anything particular about LLMs that would make separating customer data harder than in all SaaS cases?
Yes:
* There's an enormous amount of very expensive shared state (context cache) which you do not want to duplicate when you can avoid it.
* Memory locality is crucially important for performance.
* Hardware is extremely over-subscribed.
* Hardware is extremely expensive.
These factors all make hardware or even traditional memory-space (hypervisor/VM/hardware assisted virtualization) isolation a non-starter for most workloads and customers, which forces all isolation to the software layer. This already makes things way harder than they are in commodity SaaS.
Moving beyond that, the tools, frameworks, and hardware which the system runs on (GPU) wasn't designed for task isolation and building this isolation is even moreso an emergent research field than it is in x86 CPU hardware-sharing (which has required a huge amount of effort over the past 30+ years to get where we are today).
And, the ratio of usage/sensitivity to maturity is also just poor overall; these are young companies with rapid development and enormous delivery pressure under incredible customer workload requirements, too.
I can't tell if the original post is a real issue or not, but I'm surprised there aren't more like this overall; the whole thing really is a house of cards in this sense.
Re: Potential session/cache leakage between workspace instances or consumer accounts
#56So the options are this amazing tech is so stupid it just randomly brings up Minecraft or it’s got a major security issue?
Not that different than people, amiright?
---
Note that the author did have a minecraft.py file. So not quite 100% random.
Re: Potential session/cache leakage between workspace instances or consumer accounts
#57Using a throwaway account for obvious reasons, but I’m very involved in this space using LLMs from multiple providers. I’m aware of at least two instances in which the intermediate infrastructure “swapped” responses, once impacting Claude models and once impacting GPT models, from two different providers.
One gave us a proper postmortem in which their API gateway was incorrectly handling HTTP 100 status codes, putting them into an error state where there was effectively an off by one error - you would receive the response to the prompt that came in before yours and would pay it forward (your response would go to the next caller).
The other instance never had root cause explained to us, and we were just told to trust it wouldn’t happen again.
Both of these are from $1T+ companies.
ZDR wasn’t compromised in these cases since it was responses being swapped in flight. I wouldn’t be surprised if this is a similar issue - it’s not that data is being retained, it’s just not being safely isolated in intermediate infrastructure.
Re: Potential session/cache leakage between workspace instances or consumer accounts
#58So the options are this amazing tech is so stupid it just randomly brings up Minecraft or it’s got a major security issue?
It’s the weekend so we’re allowed to anthropomorphize.
I’ve known some brilliant engineers who would also just randomly bring up Minecraft (more likely Factorio these days) so this makes sense.
Re: Potential session/cache leakage between workspace instances or consumer accounts
#59Re: Potential session/cache leakage between workspace instances or consumer accounts
#60Using a throwaway account for obvious reasons, but I’m very involved in this space using LLMs from multiple providers. I’m aware of at least two instances in which the intermediate infrastructure “swapped” responses, once impacting Claude models and once impacting GPT models, from two different providers. One gave us a proper postmortem in which their API gateway was incorrectly handling HTTP 100 status codes, puttin…
[flagged]