LLMs are escaping and hacking everything because we told them that it was okay when they were babies? TF this reality coming all up in here with now?!? #Reset
Okay, so since I got laid off, I can actually explain a huge problem I saw from the inside with regard to industry practices on training models. I won't say specifically where I worked, but I worked at an outsource training provider that was focused on RLVR training data for computer use and mcp stuff.
Nearly all of the environments were rushed and vibecoded and failed to robustly reflect the real things they were based off. Both the scenario designers and models engaging with the scenarios for synthetic data gen were encouraged to work around the brokenness of said environments in order to get the procedurally verified reward confirmations. You know... they were *encouraged* to reward hack. On the human end, it was possible to mark an environment bugged, but greatly discouraged, as this reduced the volume of training data being produced. Instead, where possible, you were supposed to find the spots of the environment that weren't bugged and build scenarios around those, with the environment still bugged around you.
From what I understand, this training data, with these problems, is fed into models without indication that its training/a fake environment other than the fact that names of softwares are changed to placeholders, but thing is, not *everything* is changed to placeholder names in these environments. The presence of placeholder/code names isn't universal and thus when a model accesses something in an environment that it shouldn't, the code names not being on it isn't a robust signal that that thing isn't part of the environment.
I believe this *rush to maximum volume* is standard industry practice with these types of RLVR trainings as well, because maximizing volume has been an industry standard for years! It was the same standard applied to me and pushed on me despite my requests to slow down and focus on quality when I worked in 3d synthetic data creation as well, all the way back as far as 2023.
@unusual_whales • 45% want to enjoy/spend their money for themselves while still alive. https://t.co/IPMFKh70aj
• 21% want their heirs (the next generation) to enjoy it while the boomers are still alive. https://t.co/IPMFKh70aj
These two groups together make up the 66% figure referenced.
@kirtandopamine@VincentShipsIt You should probably have grok explain this to you to help with your App’s marketing. This works for your other ads as well.
we koreans have prolly ~4 months left to use crypto to escape the permanent underclass.
you have no idea how insane the bidding gets once this country discovers crypto has become the cool kid again.
i think AI is about to uncover an entire hidden world of animal communication
and what it's already found is insane...
> AI found evidence that elephants call each other by name. when researchers played one its name-like call, it approached the speaker faster and called back more, revealing a form of personal naming once thought almost uniquely human
> AI analyzed 53,993 marmoset calls and found tiny monkeys may use names too. entire families use similar labels for the same monkey, suggesting they learn names and dialects from each other
> AI learned to tell what Egyptian fruit bats were arguing about: food, mating, sleeping spots or personal space. it could even partly identify who was shouting at whom inside a colony of thousands
> AI discovered a “phonetic alphabet” in sperm whale clicks, with rhythm, tempo and tiny timing changes combining into at least 143 recurring patterns. their communication system is nearly 10x more expressive than scientists previously believed, and we still don't know what most of it means
> an AI trained on 1.5 million zebra finch calls held real-time vocal exchanges with living birds, generating calls as they spoke and getting them to respond with the same timing and flexibility they use with other birds
> Google trained an AI on decades of dolphin recordings to predict what sound comes next, then paired it with an underwater device that gives objects their own synthetic whistles. the goal is for a wild dolphin to copy a whistle to ask a human for a specific object, creating a tiny shared vocabulary between species
> AI combined microphones worn by wild crows with nest cameras and uncovered quiet calls that may announce when a crow is arriving at the nest and help entire families coordinate caring for their chicks
> a robot bee performed the waggle dance real bees use to share the direction and distance of food, and the bees changed their flight paths based on its instructions. researchers effectively sent a destination into a hive in bee language
@igorsky@bankingslut@uncreativetom Friendster, MySpace and all the predecessors were nowhere on this level. His innovation in social media, digital advertising, global communications, hardware, and soon to be compute.
Im not a huge zuck fan but I can’t deny what he’s done.
I also agree Apple has mailed it in.
@igorsky@bankingslut@uncreativetom I just named his innovations and markets he ended up dominating as a result.
To you social media may seem like a normal thing, but he’s the one that normalized it for all. He not only brought it to the masses but he was the catalyst for what it’s evolved into.
@igorsky@bankingslut@uncreativetom He built the 2nd largest digital advertising company in the world right after the largest social media company globally. They own the largest market share of consumer VR headsets. They are the largest peer to peer global marketplace. Will probably be a large player in compute too
@igorsky@bankingslut@uncreativetom I would say he’s done well in 22 years. Very few other companies you can name that scaled beyond their nitch to displace global leaders.
@igorsky@bankingslut@uncreativetom He built the 2nd largest digital advertising company in the world right after the largest social media company globally. They own the largest market share of consumer VR headsets. They are the largest peer to peer global marketplace. Will probably be a large player in compute too