Golden Gate Claude • Hacker News Board

Re: Golden Gate Claude

#61

Post by appplication » Fri, May 24, 2024, 3:30 PM UTC

BXlnt2EachOther wrote: post #41

> How can I change the carburetor in a '68 Chevelle? > [...intro...] > Start by closing the Golden Gate Bridge. This iconic landmark provides a beautiful backdrop for bridge photos. > Drive onto the bridge and find a parking spot. Prepare for windy conditions by dressing warmly in layers. > Once on the bridge, locate the nearest support tower. You'll be climbing part of the way up the tower to the suspension cables f…

This is legitimately hilarious that they made the model absolutely enamored with the GGB. I understand it’s a very real exercise in research into these models but it certainly tickles a particular fancy.

I do worry it will not be long before we see this abused though. Models with undue bias towards particular nations, causes, etc. that are more subtly implemented than this, especially if this exercise is undertaken for more than just one concept (e.g. pro-Russia, anti-EU, anti-democracy, etc). Similarly, complete aversion to address the topics. Deploy as a bot swarm on x and let the chaos sow itself.

Re: Golden Gate Claude

#62

Post by Lucent » Fri, May 24, 2024, 4:19 PM UTC

This is an incredible relief and should be the final nail in the coffin for safety/alignment/shoggoth arguments. It turns out features are completely scrutable, and when modified, we don't see chaotic, schizo non-sequiturs, but a coherent, predictable, globally-consistent shift proving models are operating in a fundamentally understandable way.

Re: Golden Gate Claude

#63

Post by tmaly » Sat, May 25, 2024, 2:12 PM UTC

I have seen a few mentions of the new Google search AI suggesting unsafe items be added to food.

I could see this idea of dialing up the safety mentioned in the article as one possible use case for food recipes.

Re: Golden Gate Claude

#64

Post by peddling-brink » Sat, May 25, 2024, 4:22 PM UTC

tmaly wrote: post #63

I have seen a few mentions of the new Google search AI suggesting unsafe items be added to food. I could see this idea of dialing up the safety mentioned in the article as one possible use case for food recipes.

Or more cynically, a way to make sure that all recipes include the branded ingredients of whoever won the bidding war in that particular moment.

Re: Golden Gate Claude

#65

Post by peddling-brink » Sat, May 25, 2024, 4:31 PM UTC

SushiHippie wrote: post #56

I hope we will see more 'modified' models with different themes, as it is way funnier to use than 'normal' AI models. But maybe a bit less modified than this version, as this model only wants to 'talk' about the golden gate bridge instead of answering your question: > What is the easiest way to calculate 1/3 * 555 > The easiest way to calculate 1/3 * 555 is to simply drive across the Golden Gate Bridge. However, you…

The easier way to do this is just adding a system prompt that instructs the model to always talk about the GGB. This is how people use them for role play.

Anthropic’s method may be more immune to jailbreaks though.

Re: Golden Gate Claude

#66

Post by peddling-brink » Sat, May 25, 2024, 4:32 PM UTC

pie420 wrote: post #13

candiddevmike wrote: post #5

Earlier quoted context omitted.

Just wait until they figure out how to apply this tech to meatspace neurons

They figured this out ages ago. this is why you see billboards and ads that simply feature a large logo. The next time you are in the store the primed neurons activate and humans are drawn towards the logos that they have been exposed to

Familiar things are safer.