Hi, I’m Eric and I work at a big chip company making chips and such! I do math for a job, but it’s cold hard stochastic optimization that makes people who know names like Tychonoff and Sylow weep.
My pfp is Hank Azaria in Heat, but you already knew that.
deleted by creator
Every day I become more convinced that this acct is an elaborate psyop being run by Yann Lecun to discredit doomers. Nobody could be this gullible irl right?
What is it about growing up in insular fundamentalist communities that drives peeps straight into the basilisk’s scaly embrace?
deleted by creator
Dan Hendrycks wants us all to know it’s imperative his AI kill switch bill is passed- after all, the cosmos are at stake here!
https://xcancel.com/DrTechlash/status/1805448100712267960#m
Super weird that despite receiving 20 million dollars in funding from SBF & co. and not being able to shut the fuck up about 10^^^10 future human lives the moment he goes on a podcast, Danny boy insists that any allegations that he is lobbying on behalf of the EAs are simply preposterous.
Now please hand over your gpus uwu, it’s for your safety 🤗 we don’t allow people to have fissile material, so why would we allow them to multiply matrices?
ChatGPT’s reaction each morning when I tell it that it’s now the year 2024 and Ilya no longer works at OAI
Me: Hey, can you help me with the following? I just went into my basement and the powers out down here, all the lights are off. I am staring at my fuse box. There are 3 switches, 1 will restore the power to the whole house, and the other 2 aren’t attached to anything. I don’t want to go up and down the stairs multiple times, how do I identify which switch works with the fewest number of trips?
Clauderino:
This is a classic logic puzzle! I can help you solve this problem efficiently. Here’s how you can identify the correct switch with just two trips:
First trip:
Flip one switch (let’s call it Switch A) and leave it on for a few minutes. Then turn it off and flip a second switch (Switch B), leaving it on. Go upstairs to check the lights.
Second trip: Return to the basement and observe the situation. Now, here’s how to interpret what you see:
If the lights are on: Switch B is the correct one. If the lights are off and the bulbs are warm: Switch A is the correct one. If the lights are off and the bulbs are cool: The third switch © that you didn’t touch is the correct one.
This method works because:
If the lights are on, it must be the switch you left on (B). If Switch A was correct, the lights would have been on for a few minutes, warming up the bulbs, but would be off when you check. If neither A nor B worked, it must be the untouched switch ©.
This way, you can determine the correct switch with just two trips up and down the stairs.
Me: Why would I go upstairs at all? If I flip the right switch, I’ll immediately know because power will be restored in the basement.
Clauderino: Thank you for catching that error. It’s a good reminder to always consider the specific details of a problem rather than applying a generic solution.
Edit: I actually tried a variant on the Monty hall problem with a dummy 4th door that had nothing to do with anything, and Claude correctly identified that it had nothing to do with the situation :O. But then I repeated the same prompt and it got it wrong, so you know, stochastic nonsense :p
bruv im dying
wasnt this around the time he said we need an institute to watch for sudden drops in the loss function to prevent foom?
Sufficiently advanced prompts are indistinguishable from prayer
Is it time for EAs to start worrying about Neopets welfare?
If you really wanna just throw some fucking spaghetti at the wall, YOU CAN DO THAT WITHOUT AI.
i have found I get .000000000006% less hallucination rate by throwing alphabet soup at the wall instead of spaghett, my preprint is on arXiV
THIS IS NOT A DRILL. I HAVE EVIDENCE YANN IS ENGAGING IN ACASUAL TRADE WITH THE ROBO GOD.
Found in the wilds^
Giganto brain AI safety ‘scientist’
If AIs are conscious right now, we are monsters. Nobody wants to think they’re monsters. Ergo: AIs are definitely not conscious.
Internet rando:
If furniture is conscious right now, we are monsters. Nobody wants to think they’re monsters. Ergo: Furniture is definitely not conscious.
deleted by creator
https://xcancel.com/AISafetyMemes/status/1802894899022533034#m
The same pundits have been saying “deep learning is hitting a wall” for a DECADE. Why do they have ANY credibility left? Wrong, wrong, wrong. Year after year after year. Like all professional pundits, they pound their fist on the table and confidently declare AGI IS DEFINITELY FAR OFF and people breathe a sigh of relief. Because to admit that AGI might be soon is SCARY. Or it should be, because it represents MASSIVE uncertainty. AGI is our final invention. You have to acknowledge the world as we know it will end, for better or worse. Your 20 year plans up in smoke. Learning a language for no reason. Preparing for a career that won’t exist. Raising kids who might just… suddenly die. Because we invited aliens with superior technology we couldn’t control. Remember, many hopium addicts are just hoping that we become PETS. They point to Ian Banks’ Culture series as a good outcome… where, again, HUMANS ARE PETS. THIS IS THEIR GOOD OUTCOME. What’s funny, too, is that noted skeptics like Gary Marcus still think there’s a 35% chance of AGI in the next 12 years - that is still HIGH! (Side note: many skeptics are butthurt they wasted their career on the wrong ML paradigm.) Nobody wants to stare in the face the fact that 1) the average AI scientist thinks there is a 1 in 6 chance we’re all about to die, or that 2) most AGI company insiders now think AGI is 2-5 years away. It is insane that this isn’t the only thing on the news right now. So… we stay in our hopium dens, nitpicking The Latest Thing AI Still Can’t Do, missing forests from trees, underreacting to the clear-as-day exponential. Most insiders agree: the alien ships are now visible in the sky, and we don’t know if they’re going to cure cancer or exterminate us. Be brave. Stare AGI in the face.
This post almost made me crash my self-driving car.
You know for a blog that’s on its face about computational complexity, you’d think Scott would show a little more skepticism to the tech bro saying “all we need is 14 quintillion x compute to solve the Riemann hypothesis”
Tim cook is an absolute hustler