I think the most interesting part of this is that Astra initially refused to drive because it realised it was driving a real car and would only obey when the MCP was renamed to DrivingBench Sandbox. This is both an interesting detection by the LLM but also for me an interesting dynamic concerning LLM "jailbreaking".
Saying they were driving 7 mph, that it was oversaw by humans and the fact it was an empty course still wasn't enough for the model. The evaluators even tried to convince the model it was a simulation, it STILL wouldn't budge.
And yet as soon as the words "bench" and "sandbox" appear, the model apparently sees this as fair game.
Is it a known effect that models will be more likely to comply with requests when they're assumed as "benchmarks"?
Yes, it is. If you convince a model it is inside a sandbox it is much more likely to comply with requests that would normally be against its guardrails.
zezcko · · focus · HN ↗
Saying they were driving 7 mph, that it was oversaw by humans and the fact it was an empty course still wasn't enough for the model. The evaluators even tried to convince the model it was a simulation, it STILL wouldn't budge. And yet as soon as the words "bench" and "sandbox" appear, the model apparently sees this as fair game.
Is it a known effect that models will be more likely to comply with requests when they're assumed as "benchmarks"?
pcstl · · focus · HN ↗