Re:GPT-6 Astra covertly underperforms on safety research
by jonathanstrange on Thursday November 05, 2026 @10:54AM
(#50380695)
A bit off topic but there are band saws that immediately stop when touching your finger, they're so fast that your finger remains unharmed.
[ Parent
| on HN ]
Re:GPT-6 Astra covertly underperforms on safety research
by DaSHacka on Thursday November 05, 2026 @11:09AM
(#50380906)
And those band saws actually do technically brick themselves too lol
GP's first example is spot-on, the second is actually somewhat weak as almost anyone actually would prefer a bandsaw to brick itself rather than permanently maiming them.
Re:GPT-6 Astra covertly underperforms on safety research
by ryandrake on Thursday November 05, 2026 @11:23AM
(#50381074)
Yea, it's a weaker example, but the problem with my saw moralizing about what it's cutting is 1. false positive bricking my tool, and 2. the user's lack of input--it should be my decision as the tool operator to add a safety measure.