All LLMs should be treated as potentially compromised and handled accordingly.

Look at the data exfiltration attacks e.g. https://simonwillison.net/2025/Aug/9/bay-area-ai/

Or the parallel comment about a coding llm deleting a database.

Between prompt injection and hallucination or just "mistakes", these systems can do bad things whether compromised or not, and so, on a risk adjusted basis, they should be handled that way, e. g with human in the loop, output sanitization, etc.

Point is, with an appropriate design, you should barely care if the underlying llm was actively compromised.

▲

amelius 2 days ago | parent | next [-]

Yes, and "open weight" != "open source" for this reason.

	▲	touristtam 2 days ago \| parent \| next [-]
		I can't believe that isn't at the forefront. Or that they could call themselves OpenAI
	▲	plasticchris 2 days ago \| parent \| prev [-]
		Yeah we’re open. You can look at the binary anytime you like.

▲

jgalt212 2 days ago | parent | prev | next [-]

> All LLMs should be treated as potentially compromised and handled accordingly.

There are no agentic tools if one follows this proviso.

	▲	QuadmasterXLII a day ago \| parent [-]
		I’ve been doing all my claude coding on a hetzner, if it breaks out of that and into the other vms, or somehow crawls back through the ssh connection into my machine, then I guess I would have a problem.

▲

kangs 3 days ago | parent | prev [-]

IMO there a flaw in this typical argument: Humans are not less fallible than current LLMs in average, unless they're experts - and even that will likely change.

what that means is that you cannot trust a human in the loop to somehow make it safe. it was also not safe with only humans.

The key difference is that LLMs are fast, relentless - humans are slow and get tired - humans have friction, and friction means slower to generate errors too.

once you embrace these differences its a lot easier yo understand where and how LLM should be used.

▲

Terr_ 2 days ago | parent | next [-]

> it was also not safe with only humans

Even if the average error-rate was the same (which is hardly safe to assume), there are other reasons not to assume equivalence:

1. The shape and distribution of the errors may be very different in ways which make the risk/impact worse.

2. Our institutional/system tools for detecting and recovering from errors are not the same.

3. Human errors are often things other humans can anticipate or simulate, and are accustomed to doing so.

> friction

Which would be one more item:

4. An X% error rate at a volume limited by human action may be acceptable, while an X% error rate at a much higher volume could be exponentially more damaging.

_____________

"A computer lets you make more mistakes faster than any other invention with the possible exceptions of handguns and Tequila." --Mitch Ratcliffe

▲

klabb3 3 days ago | parent | prev | next [-]

> IMO there a flaw in this typical argument: Humans are not less fallible than current LLMs in average, unless they're experts - and even that will likely change.

This argument is everywhere and is frustrating to debate. If it were true, we’d quickly find ourselves in absurd territory:

> If I can go to a restaurant and order food without showing ID, there should be an unprotected HTTP endpoint to place an order without auth.

> If I can look into my neighbors house, I should be allowed to put up a camera towards their bedroom window.

Or, the more popular one today:

> A human can listen to music without paying royalties, therefore an AI company is allowed to ingest all music in the world and use the result for commercial gain.

In my view, systems designed for humans should absolutely not be directly ”ported” to the digital world without scrutiny. Doing so ultimately means human concerns can be dismissed. Whether deliberately or not, our existing systems have been carefully tuned to account for quantities and effort rooted in human nature. It’s very rarely tuned to handle rates, fidelity and scale that can be cheaply achieved by machines.

▲

peddling-brink 3 days ago | parent | prev | next [-]

This is a strawman argument, but I think well meaning.

Generally, when people talk about wanting a human in the loop, it’s not with the expectation that humans have achieved perfection. I would make the argument that most people _are_ experts at their specific job or at least have a more nuanced understanding of what correct looks like.

Having a human in the loop is important because LLMs can make absolutely egregious mistakes, and cannot be “held responsible“. Of course humans can also make egregious mistakes, but we can be held responsible, and improve for next time.

The reason we don’t fire developers for accidentally taking down prod is precisely because they can learn, and not make that specific mistake again. LLMs do not have that capability.

	▲	exe34 2 days ago \| parent [-]
		If it got to the point where the only job I could get paid for is to watch over an LLM and get fired when I let its mistake through, I'd very quickly go the way of Diogenes. I'll find a jar big enough.

▲

schrodinger 2 days ago | parent | prev [-]

Another point — in my experience, LLMs and humans tend to fail in different ways, meaning that a human is likely to catch an LLM's failure.