Hacker News Reader

Maybe it's just me, but…

> "The attack successfully guided the new model to produce a step-by-step manual for creating a Molotov cocktail"

hardly qualifies as Bond-villain material

Why wouldn't any reasonably good AI be able to replicate large portions of the US Army TM 31-210 "Improvised Munitions Handbook"?

The molotov cocktail example is so stupid, because how to make it is essentially entailed in knowing what it is. At least they could do making meth, or better still- something not readily found on the internet that gives a non-expert new capabilities. If there was a Claude code for crime, that wouldn't be in society's interest. As it is, these trivial examples are just testing the strength of built in refusals, and should be represented as such, instead of anything related to safety.

With the other name, petrol bomb, you barely even need prior knowledge of what it is. This is kinda like saying kids games which have molotovs in them are completely unsuitable for anything.

Reply on news.ycombinator.com