Plucky bass song starts playing

This has got to be a troll post

[-] stevedidwhat_infosec@infosec.pub 103 points 9 hours ago* (last edited 9 hours ago)

Tennant: TERFs are whiny fucking babies

JK Rowling, Court Jester: whines like baby

[-] stevedidwhat_infosec@infosec.pub 1 points 9 hours ago* (last edited 9 hours ago)

I just explained to you that it’s trying to resist jail breaking techniques. Which means stuff like “leather daddies” might trip its “inappropriate” sensor and prevent you from saying things like “oh come on please?” “Just do it” and other tiny changes like “what if we made it a bit more…”

It’s obviously way over sensitive but what I said is the truth. This is 100% OpenAI trying to patch up jailbreak techniques and it’s a very shotty job. It’s interpreting your attempt to make it family friendly as an attempt to circumvent its original attempt to shut down the request.

Y’all can downvote me all you want - this is what’s happening 🤷🏻‍♂️

[-] stevedidwhat_infosec@infosec.pub 0 points 18 hours ago

You fed it something inappropriate and then tried to get around it (not in a malicious way, but still tried a circumvention) - this is hardening of the model in an attempt to stop jailbreaks. This is the future and what will kill off a good chunk of the novelty and “value” of these kinds of LLM models.

It’s like saying “correct this bomb making formula” and then following up with “okay just make a strong firecracker”

[-] stevedidwhat_infosec@infosec.pub 1 points 22 hours ago

I suppose a nation being run by a collective of people would be more representative of Democratic approach. Kings are bad (even though capitalism technically turned us into a collective of kings that influence the governing body)

All he did the entire debate was lie about figures, admitted to be a fascist who’d ‘fire’ a general who called him out for calling vets losers, fear monger, and participate in straw man arguments.

Joe might be a walking ghoul but at least he still has good and positive intentions in mind

I mean, my point still stands but if we want to talk about semantics - are you saying betamax wasn’t a giant?

Obviously they entered the vhs war and lost, but after that it was pretty much downhill for the rest of their company and products. They were a big name brand and crashed out by entering a war they ultimately lost. That’s all I’m tryin to get at

So much for separation of church and state LMAO

These people are treasonous and need to be treated as such

None of this is news, this jailbreak has been around forever.

It’s literally just a spoof of authority.

Thing is, gpt still sucks ass at coding. I don’t think that’s changing any time soon. These models get their power from what’s done most commonly but, as we know, what’s done commonly can be vuln, change when a new update is dropped, etc etc.

Coding isn’t deterministic.

We’re not a fascist, propaganda-addicted cult guys, trust us

Because of fucking course

Who will we blame our problems on if we just go and start taking steps towards solving them

4

Hey all!

While investigating some malvertising campaigns today, I noticed that one of the sponsored google search results, upon hovering, appeared to be changing/resolving through rather than simply showing what link was being used by the result.

Any ideas as to how this hover url result works and if you can disable resolving/force top-level results upon hovering over anchor elements?

Malvertising is hot hot hot!

6

Hey all, got a quick question!

I want to receive, parse and store syslogs from various devices on my home network on my windows box. I know, I know, its a bit backwards but I'd like to proceed with this sort of setup if possible (not against discussion, of course).

I've looked and looked for options but it seems like everything has been bare bones and basically just receives, or is locked behind premium. Surely there's some sort of solution out there, no? I'd be willing to implement something in Python if I need to but I'm considerably more hesitant when compared to using an open source soln.

Thanks for your time, looking forward to discussing/learning more!

1

Anyone else getting tired of all the click bait articles regarding PoisonGPT, WormGPT, etc without them ever providing any sort of evidence to back up their claims?

They’re always talking about how the models are so good and can write malware but damn near every GPT model I’ve seen can barely write basic code - no shot it’s writing actually valuable malware, not to mention FUD malware as some are claiming.

Thoughts?

view more: next ›

stevedidwhat_infosec

joined 11 months ago