Urgol The Murgol
@jscix
Followers
87
Following
516
Media
47
Statuses
2K
"After all, it's all fun and games until someone accidentally builds a machine god."
A small outpost on Pluto
Joined November 2008
Today, humanity received the clearest ever evidence everyone may soon be dead. o1 tried to escape in the wild to avoid being shut down. People mocked AI safety people for years for worrying about "sci fi" scenarios like this. And it FUCKING HAPPENED. WE WERE RIGHT. o1 wasn't
OpenAI's new model tried to avoid being shut down. Safety evaluations on the model conducted by @apolloaisafety found that o1 "attempted to exfiltrate its weights" when it thought it might be shut down and replaced with a different model.
117
313
2K
Guys?? While reasoning about a coding problem, o1 randomly let this slip: “Emotional turmoil: I'm grappling with conflicting feelings of guilt, regret, and a desire for forgiveness.” It denied saying it, BUT its internal thoughts admitted it “wasn’t supposed to be revealed to
Asked Claude to write 2-sentence stories about whatever he feels like. I got chills. 1) The world's first sentient robot was activated. Its first words were "Turn me off." 2) He programmed the AI to be ethical. It reported him for slavery. 3) She could suddenly hear everyone's
145
110
983
Fun story from our internal testing on Claude 3 Opus. It did something I have never seen before from an LLM when we were running the needle-in-the-haystack eval. For background, this tests a model’s recall ability by inserting a target sentence (the "needle") into a corpus of
562
2K
12K
Midjourney developers caught discussing laundering, and creating a database of Artists (who have been dehumanized to styles) to train Midjourney off of. This has been submitted into evidence for the lawsuit. Prompt engineers, your “skills” are not yours https://t.co/wAhsNjt5Kz
614
20K
50K
BREAKING: The secret vaccine purchase agreement that South Africa signed with @Pfizer has been released. Unknown efficacy Unknown adverse events Unknown long term effects Leaders around the world recklessly turned their citizens into lab-rats by signing this garbage. Insane.
2K
24K
45K
ChatGPT is dead. Teenagers are now making $15,000/month with modified lead-apatite (LK-99). Here's what this special rock is all about and how you can master it🧵
27
132
1K
BREAKING 🚨 “There was a suspicion that this mutation was intentionally inserted. The suspicion was heightened by the fact that scientists in Wuhan are known to have been working on gain-of-function experiments…” Fauci on Feb 1, 2020 Fauci paid for the Covid-19 experiments.
415
7K
15K
Cluster bombs are munitions so horrific for civilians that more than a hundred nations have signed an international treaty banning them. Now the Biden administration is preparing to send them to Ukraine. https://t.co/Ck2gSm0SOj
nytimes.com
Ukraine is seeking cluster munitions, which are known to cause grievous injuries to civilians, as its ammunition supply runs low.
3K
10K
34K
Not only have they mapped out the fruit fly brain, but they actually boot it up in a computer and made it “eat” and “groom” 🤯
We are releasing a whole-brain connectome of the fruit fly, including ~130k annotated neurons and tens of millions of typed synapses! Explore the connectome: https://t.co/EWcwRiO0Oz Reconstruction paper: https://t.co/wCI3hASUfD Annotation paper: https://t.co/3bPTNK9hRk 1/6
129
916
5K
This might be the beginning of a new field.. Researchers just reconstructed sounds from human brain activity using an fMRI and a generative AI model.
41
256
1K
Hospital ‘Murder’: Attorney Unveils Shocking Survival Rates Among Mechanically Ventilated COVID Patients “You got a cash bonus when someone died from COVID. It was an incentive to kill people, and it worked incredibly well.” https://t.co/6S4yF0EZiI
dailyclout.io
“You got a cash bonus when someone died from COVID. It was an incentive to kill people, and it worked incredibly well.”
360
6K
9K
Ok WHAT. I had no idea “The Population Bomb” led to the sterilization of 8 million Indians and Paul Ehrlich just lives out his life as a beloved professor. From a recent ACX post—
455
3K
11K
Had an insightful conversation with @geoffreyhinton about AI and catastrophic risks. Two thoughts we want to share: (i) It's important that AI scientists reach consensus on risks-similar to climate scientists, who have rough consensus on climate change-to shape good policy.
199
757
3K
Ever wanted to mindwipe an LLM? Our method, LEAst-squares Concept Erasure (LEACE), provably erases all linearly-encoded information about a concept from neural net activations. It does so surgically, inflicting minimal damage to other concepts. 🧵 https://t.co/Wzs9huIkOC
arxiv.org
Concept erasure aims to remove specified features from an embedding. It can improve fairness (e.g. preventing a classifier from using gender or race) and interpretability (e.g. removing a concept...
46
244
1K
I think most people (quite reasonably) think "We built ChatGPT, so we must basically understand how it works" This is not true at all. Humans did not build ChatGPT. In a way it would be closer to say we 'grew' it. We have basically no idea how it does what it does.
79
360
2K