this post was submitted on 21 Apr 2024
31 points (100.0% liked)
TechTakes
1384 readers
199 users here now
Big brain tech dude got yet another clueless take over at HackerNews etc? Here's the place to vent. Orange site, VC foolishness, all welcome.
This is not debate club. Unless it’s amusing debate.
For actually-good tech, you want our NotAwfulTech community
founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
????
https://www.anzacsquare.qld.gov.au/virtual-veterans
The anzacs are venerated for being thrown into the meat grinder by accident, them being fodder for an AI chatbot is what they would have wanted
As triumphalist national myths go, this one being "yeah, we lost so fuckin badly" has always struck me as inherently hilarious
Not only did we get fuckin stomped, we did it with a smile on our face for Mummy Britannia. We’re a nation of subs!
nation of subs surely would handle procurement of Collins-class replacement better, 15? years on and no new submarines delivered, only thing it did was to annoy french
or maybe just add "humiliation" to the list of kinks and go on
can you get Charlie to help you write Python tho
If you ask it nicely, yes.
took me five or four prompts for charlie to explain json schemas to me.
…this clearly broke the rules enough, and we have the first effect:
…and here it goes.
you know, it'd be a damn shame if someone made one of those megalists which contained all the various places that had promptboxes that could be used to synthesize bad code without having to pay your own money to openai subscriptions or so
tired: stealing hundreds of dollars of electricity to mine hundreds of pennies in crypto
wired: spiking some project manager’s OpenAI bill to unsustainable levels by having their chatbot generate the worst nonsense ever experienced by a human
inspired: crowdsourced prompt-based captcha solving
it feels a little mean doing this to a library, even if their use of AI is obviously doomed to failure, so a list of public access GPT prompts would be a service.
Yeah, hospitals/libraries/schools/etc should not be things on such a list generally
(In two minds about some of the US colleges, but that’s a different kettle of barbs)
As soon as some of these LLMs get a math module to do math correctly (And not just via the LLM lookuptable thing) people could write scripts to externalize some more intensive calculations needed for crypto mining. Sure it will be inefficient as fuck, and I doubt the chance of getting a coin reward will be low, but it will be free.
last week there were a couple of articles about how easy it is to craft an input that makes public chatgpt bots execute scripts (usually as root) on their hosting containers, which is almost definitely the result of a module like that being implemented for better programming-related results (aka fucking cheating), so this is very likely already happening
Happy to at least not be the first to think of that idea, and sad to hear people will wreck the commons more.
WHAAAT
links plz?
found the original post! https://mastodon.social/@kennwhite/112290497758846218 the prompt to make them execute code is incredibly basic. no idea right now if the exploit is in the chatbot framework or the model itself though
oh shit, somehow I figured you knew already! I’ll skim through my browser history and masto boosts and see if I can find one of the articles
counterpoint: it gives openai more money
not necessarily/could be offset? openai is still in that "we'll set fire to money to make ourselves look good" stage of VC dreamery; find entities operating on credits, slap there
but possibly even in the case where it's still straight transactional, it might be a net negative for them: revenue, actual usage, and still no meaningful shift on their product becoming good. it'll just make them look even worse
the bigger problem (to which this suggestion would most certainly contribute things getting worse) is that they're still burning other important resources. I don't really have a good/clever proposal to this which isn't something like "well, burn their DCs to the fucking ground" (or other more creative forms of invasive service interruption)
they will burn through that money pretty quickly and without turning profit, however this can contribute to one of their ratfucked metrics to go up, which could hype up some segment of stonk market. because now they're fueled by hype and vc money, any new thing that would sustain that hype would be a bad thing (adoption here, kinda, at least as seen through excel)
i agree, 120mm mortar is much cheaper, faster, more irreversible, but openai going bankrupt and forced to sell their kit at least would generate less waste
and a net positive in terms of human happiness
Hahah well done!
lol holy shit