RoRo
PwnallthethingsSo these AI chats are pretty cool.
One thing that's gonna cause some problems tho is that they sound really really convincing while sometimes being extremely extremely wrong
A zillion ways this revolution is going to be great.
One way that's going to suck tho is in places where human interactions are a *useful* friction / proof-of-work. When it's not, those systems will get really overloaded
Few examples:
1. Online troll bots & fake personalities
It's going to get a *lot* harder to distinguish bots from people and much easier to create entirely fictitious credible online personalities to troll/harass/do crime
2. Persuasive letters by e.g. constituents to regulators.
Volume of (~sensible, unique) letters was a valid indication of sentiment. Soon won't be.
3. Ransomware victim communications & negotiations
Used to be one of the few costly areas in scale. Not for long
4. Places where writing is assessed for cash or credit
Going to be much easier for e.g. students to fake/plagiarize essays or other homework for-credit
Combatting that will probably eventually force schools and universities towards towards more heavy focus on proctored work (exams, supervised essay writing) (ugh)
Going to be much easier to create fake-news clickbait farms too for ~ the same reason
What worries me a bit here is that in trying to preserve some of these systems, there'll probably be a lot of folks pushing tech designed to *prove* humanness to combat it. And politicos and regulators are less likely to hear that and think "guess they should use creative CAPTCHAs" and more likely to think "oh, people should upload passports", and that's gonna be a whole new shitshow
Also excited for the new era of "who is liable when the AI tells you to cook the frozen Turkey in the deep-fryer" / "can you maliciously interact as user A with the AI, such that the AI interacts with user B and advises them to do X" wars
Anyway. New world. New cool stuff. New unforeseen challenges. Gonna be weird.
Gonna add one point to this, since it's easy to focus on the downsides. There's some great stuff too.
One way AI is going to be *fantastic* is for accessibility. Imagine, for example, tools that summarize pictures as the default text for alt-text fields, making it faster and easier to make apps and sites accessible by default.
Another is making cool learning technologies, especially for beginners. Turning text into example code and vice-versa is a great learning tool!
And enabling technical creativity, especially by young folks / non-tech folks.
Imagine kids can *describe* a level they want to play as the starting point for making games to share with each other.
So, yes, big change comes with new risks, but also no shortage of new opportunities.
Alas, like most change, will be hard to see exactly how those shoes drop and the balance shifts across society in response until they do though.
That Anonymous CowardI think we shoudl rethink the Turing Test.
I think a much more valid test would be any AI that can understand & explain copyright law without exploding.
!Eirick@That_AC @Pwnallthethings lol. It's just whatever laws Disney can get passed to keep the mouse from going into public domain. Love how those laws change whenever Mickey is about to be used royalty free.
As the AI delivers the answer...
The first thing we do, is kill that damn mouse.
Mikarnage@That_AC @Pwnallthethings can any human do that?
Nope. Which is why any AI able to competently do it would be more advanced than any human brain.
@That_AC @Pwnallthethings yes, I think Turing test is slowly becoming irrelevant, as IAs are already much better than humans at certain tasks and still completely stupid for some other.
Alexandra Brown@Pwnallthethings agreed; and for folks who find writing/reading hard or unpleasant, having a robot to express your intent for official letters, writing apologies etc is going to be great!
PB Livin'@AlexBBrown @Pwnallthethings 💯 I have a hard time putting my thoughts into writing - I know what I want to say, but turning it into well structured sentences takes a long time for me.
I'm great at explaining things when I'm talking to someone, cuz it's easier to jump around in my thoughts and still have someone be able to follow my train of thought. But writing it out is hard.
Would be amazing if I could say it to an AI, and it returns it in well written sentences for me. 🤩
Allan Chow@Pwnallthethings the scope of such a thing needs to be contained otherwise you can quickly get into a djinn giving you a million bucks or a 10 inch pianist territory quickly.
@Pwnallthethings this is something pixel press should look into!
http://www.projectpixelpress.com/#left-and-right
http://www.projectpixelpress.com/#left-and-right
S★m V★rm★@Pwnallthethings
I was at an event this weekend for a biotech company that uses AI to create novel cancer treatments. Everyone at the table was convinced this is a net good for society, and that the field of medicine is more equitable than other tech-adjacent spaces. I argued that, just like everything else, the benefits will split 80/20, with the lower 80% of the population getting only 20% of the benefit.
I believe that #AI will disrupt faster than any rebalancing across society.
@Pwnallthethings it's shockingly good at just taking descriptions of a text adventure and generating an entire game. I asked it for a Thomas Hardy-based text adventure here:
@Pwnallthethings literally all of that is just its own freestyling. I could have followed up and asked it to add some NPCs with branching dialogue and it would have done. You can use it to generate crappy edutainment in next to no time ("generate a python a text adventure adaptation of *A Tale of Two Cities" where the player can interact with the characters and ask them about their lives and philosophies" would probably work)
RachelI just uploaded some screenshots with text, and clicked the add alttext automatically, and it did a pretty great job!
Would be neat for people viewing the post to have the same button!
Daniel Howard 🌻@Pwnallthethings In the day, folks were concerned that writing would destroy our ability to think because we wouldn't have to keep everything in our heads. That's a fair concern, too. And the world keeps turning.
jakenuts@Pwnallthethings just a semi-expert teacher who can instantly adapt to whatever skill level and language the student is at is a wonder. Wish it could draw boxes and arrows while it spoke..
🦄 Vlt (Cédric Hebert) 🇫🇷@Pwnallthethings The training aspect is great, let's see where this will go. The AI created a CTF challenge and it's write-up upon my request, but the answer came with a "this request might violate our code of conduct".
I hope infosec learning won't be sacrificed in the name of security!
I hope infosec learning won't be sacrificed in the name of security!
Dante Mercurio@Pwnallthethings Text to example code is a very cool use case. I’d look forward to that.
IsWackyI asked of openai playground bot the following request:
Ralph Nader said, "Republicans stab you in the front." The implication is that Democrats stab you, the voter, in the back. Please show examples of republicans stabbing you in the front.
It puzzled out the Q and gave a good answer!
(Cont'd)
Examples of Republicans stabbing you in the front include:
1. Attempting to pass legislation that would cut taxes for the wealthy and big corporations while cutting government assistance programs for the middle and lower classes.
2. Attempting to pass legislation that would roll back regulations on corporations, while leaving individuals and small businesses unprotected.
(Cont'd)
(Cont'd)
3. Refusing to pass meaningful gun control legislation, instead choosing to make it easier for dangerous individuals to obtain firearms.
4. Pushing for deregulation of the banking and financial industries, leading to the 2008 financial crisis.
5. Supporting policies that would weaken labor unions and make it harder for workers to get fair wages and benefits.
Brian Grinter@Pwnallthethings it would make it easy to add alt text here
But you just know some will abuse it for all the wrong reasons
bigiain@Pwnallthethings This could make adversarial image attacks fun again!
⁂ Fish Id Wardrobe@Pwnallthethings tools that summarise pictures in a way that "sounds convincing but can be really really wrong"…?
Rachel@Pwnallthethings
I just uploaded some screenshots with text, and clicked the add alttext automatically, and it did a pretty great job!
Would be neat for people viewing the post to have the same button!
I just uploaded some screenshots with text, and clicked the add alttext automatically, and it did a pretty great job!
Would be neat for people viewing the post to have the same button!
Jordy 
@Pwnallthethings gonna be super weird. 🫣
subdee@Pwnallthethings I think we might see the age of letters again. all important work/secure work will have to be done face to face... I also kinda worry what's gonna happen to the kids on the internet surrounded by sophisticated word salad and if THEY'LL be able to tell the difference or if they'll also start talking like bots/trolls/advertisers and it'll be even harder to tell computer and human apart
WndlB@Pwnallthethings Go though a Good Housekeeping/Underwood Labs 'Seal of Approval' portal?
Adam Shostack 
@Pwnallthethings "It is not recommended to cook a frozen turkey in a deep fryer. Turkeys should be thawed completely before being cooked in a deep fryer to ensure even cooking and prevent the risk of fire...."
Ken Hoyme
Never Deep-Fry A Frozen Turkey
Mark Gardner
Elmo Musk@mjgardner @Pwnallthethings 100%! If your software tells people to kill themselves, it doesn't matter if you hardcoded it, or created 100 if-then's to get there, or created a black-box that ends up saying that, YOU should be liable for its actions. Otherwise it's pretty easy to deny ANY responsibility and accountability by saying "OOPS sorry not our bad, the mean mean computer did it!"
@rooneel @Pwnallthethings I suppose also and/or more liable would be whoever gave the developer/trainer their marching orders
Brad Wilson@mjgardner @Pwnallthethings With the help of Pikachu, I presume. 😂
@krisnelson@Pwnallthethings I will say that as of now, of all the worries people express about AI, who is liable is one of the lower on my list. It won’t take very long for lawyers to sort this out—and we’ll just start by suing absolutely everyone in sight to see what it sticks to, probably beginning with the theory they (programmers, host, referrer, everyone) are all jointly and severally liable for anything and everything.
Andrei Kucharavy@Pwnallthethings you don’t want to know how easy are those models to hijack, especially on niche topics. At some point on Twitter I had a thread of Google search results that had artifacts due to errors in parsing or short-term fads that affected search results in a durable manner by creating an association between terms.
Given the linguistic specificity of different population sub-groups, you can also target the hijack to a specific sub-group you might need to influence/hurt/…
Given the linguistic specificity of different population sub-groups, you can also target the hijack to a specific sub-group you might need to influence/hurt/…
ScatalogicAI@Pwnallthethings
I don't understand why the AI keeps telling me to put a Sharpie in my butt.
I don't understand why the AI keeps telling me to put a Sharpie in my butt.
Nour Agha 
@Pwnallthethings At this point, some digital passport standard in the future feels inevitable.
@Nour Probably. Also I hate it.
@Pwnallthethings It already sort of exists with stuff like Keybase and Keyoxide where you cryptographically verify your social identities and online presence, so I imagine governments would use a standard that builds on top of that. But
yeah.
yeah.
Enrique Barcelli@Pwnallthethings
Have been thinking about this issue too, and I don't see how we can effectively prove we are humans through a software endpoint which is also available to a bot, unless we have a global/national complete record of humans identified with private/public keypairs.
AI is already capable of defeating our most creative CAPTCHAs.
These efforts are already existing in some countries. #Singapore #SingPass is actually this.
1/2
@Pwnallthethings
This will require also that some bits of the 'security protocol' be done in person in front of another human beings.
2/2
David J. Atkinson
Steve@Pwnallthethings That latter one is going to suck. While systems like turn-it-in served the last 2 decades well for catching plagiarism, they really can't work with "an AI generated this to be genuinely unique, but not demonstrate student knowledge on the subject"
Wry Shupe 🌲@Pwnallthethings
The educators in all areas I speak to are trying to get a handle on this.
Flipped curriculum (lectures recorded, classes proving comprehension in lab form) is actually how I'd like to learn if I was going to school again, and addresses this.
Unfortunately it also likely pressures people with learning styles that don't do well in that environment.
@Pwnallthethings It’s OK, the textbooks and lectures will be #AI - generated too
aresso you're saying we could automate discussions with reinstated haters on the other place
even more diabolical than shadowbans
Joe Uchill@Pwnallthethings Me too, AI. Me too.
@Pwnallthethings As someone else said, all it needs to give a TED talk is adding inspirational background graphics
as with self-driving, ai chats don't have to be perfect, they just need to be better than the average human
Cassandrich@Pwnallthethings So they're competing with the orange site?