Live data from Hacker News

Potential session/cache leakage between workspace instances or consumer accounts

github.com

31–40 of 151 posts

Re: Potential session/cache leakage between workspace instances or consumer accounts

#31

Is there anything particular about LLMs that would make separating customer data harder than in all SaaS cases?

Vibe-coding the implementation. I haven't had much issue with Codex, but seems Claude Code has major issues being reported nearly on the daily. They also happen to be the most boastful about not reading or looking at the code. LLMs are very capable, but not nearly to the level they seem to be messaging. (We've actually moved on from vibe-coding to having the LLM vibe code itself in a loop)

> having the LLM vibe code itself in a loop

The businesslatin name for this is Recursive Self-Improvement

Re: Potential session/cache leakage between workspace instances or consumer accounts

#32
post #10

Earlier quoted context omitted.

While abused by LLM vendors, that phrase in one form or another I've been hearing since the early '00s and it's likely way older.

Sure but have you ever seen it actually play out in practice like it currently is? Whether or not it's true (of course it's not) people are currently behaving as if it is and firing/hiring accordingly.

Well, when was the last time you wrote machine code by hand?

... but then they went and changed what coding meant.

We've always been layering abstractions on top of abstractions. If we get to an abstraction that works well enough that you no longer have to dive down into the previous layer, we say we've solved coding, and change what coding means. Obviously LLMs aren't there yet.

Re: Potential session/cache leakage between workspace instances or consumer accounts

#33
post #5
post #3

Oh yes, we do not need programmers any more…

"Coding is largely solved"

The funny thing is at my current employer, they mentioned that "coding is increasingly becoming a solved problem" and in the same breath, mentioned that one project was too hard for anyone to do so they're not doing it and would rather sell existing features...

Re: Potential session/cache leakage between workspace instances or consumer accounts

#34

Is there anything particular about LLMs that would make separating customer data harder than in all SaaS cases?

Vibe-coding the implementation. I haven't had much issue with Codex, but seems Claude Code has major issues being reported nearly on the daily. They also happen to be the most boastful about not reading or looking at the code. LLMs are very capable, but not nearly to the level they seem to be messaging. (We've actually moved on from vibe-coding to having the LLM vibe code itself in a loop)

Interestingly I had an almost identical experience to this report in codex. It output a user memory file that looked awfully real and wasn't at all related to my work.

Re: Potential session/cache leakage between workspace instances or consumer accounts

#35

In order Fable 5 has rejected: "Recipe for red-braised pork, I have pork shoulder" "Write up a framework for MCP patterns I can give to claude code" "explain the biomechanics of motion in c. elegans" (I get this one, I mostly did it to test and it's related to my hobby project) Do we get an extra day of functional Fable 5 because it's down?

What does this have to do with anything? Who are you talking to? This is Hacker News, not Anthropic support.

Re: Potential session/cache leakage between workspace instances or consumer accounts

#36
post #2

Sounds 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…

I realize hallucination has no precise definition but this doesn’t sound at all like anything I’ve ever heard called hallucination. Hallucination is usually plausible wrong answers or made up info that ends up fitting the most likely response (like a manufactured citation) and comes from the way LLMs work at predicting tokens. This example demonstrates completely implausible output, it’s not something that fits with hallucination.

All that said, it doesn’t require cross session leakage, it could just be training data or like those nightingale (probably the wrong bird*) data generations where they just prompt an LLM with nothing and it starts spitting out conversations.

I see a bunch of downstream comments about caching, sounds like maybe there’s an error where it loads nothing instead of the cache and so starts spitting out random generations.

* edit: it’s magpie. Worth looking at the concept, I’m not sure people realize they LLMs generate random conversations when prompted with nothing, this seems at least as likely as sessions leaking: https://github.com/magpie-align/magpie

Re: Potential session/cache leakage between workspace instances or consumer accounts

#37

In order Fable 5 has rejected: "Recipe for red-braised pork, I have pork shoulder" "Write up a framework for MCP patterns I can give to claude code" "explain the biomechanics of motion in c. elegans" (I get this one, I mostly did it to test and it's related to my hobby project) Do we get an extra day of functional Fable 5 because it's down?

Not sure the relevance of this comment, but normally if someone built a classifier that bad they’d be fired. Anthropic obviously thinks they have some monopoly power they can use to foist garbage on consumers, I think they don’t.

Re: Potential session/cache leakage between workspace instances or consumer accounts

#39
post #3

Oh yes, we do not need programmers any more…

it’s the wet dream of execs and pm types. however, i have not seen anything close to it in my life. I remember the UML days, lol. the issue is not the code, it’s the translation layer between business and code. maybe someday ai bridges that gap. history has shown probably not
Post reply on HN