Boldbug retweeted
An internal model at OpenAI has produced a claimed refutation of ETH! Russell Impagliazzo, Mohan Paturi, and I have been asked to help organize an open and independent examination of this claim. 1/4
Now this is something I aim for
I see how some people can watch flashy robot demos on the timeline and think with a shiver that the robot apocalypse is around the corner, but reality check:
There is no robot in the world that can change the batteries in a jack-o-lantern.
If you have a robot friendly door handle it might be able to walk outside, pick it up, and carry it back inside. The robot could open the drawer with your batteries in it, but then things get tough.
Opening the package of AA batteries?
Extracting a precision screwdriver from its case?
Unscrewing four tiny screws that require a hard press and twist?
Popping batteries out of the case?
Yes, you could build and train a specialist robot to do that today, but there is a very long way to go to replace the full range of human capabilities. Near term doomer scenarios should stop at “secretly controlling humanity” instead of “wiping humanity out” 😀
Replying to @spisallyouneed @skyfallai
its my dream to work on world models , thats why i started learning ML and am progressing rapidly. i hope to work with a team like this one day and hopefully find a good mentor
Replying to @GoogleColab
@GoogleColab why is this happening?i cannot use colab.
Replying to @OscarMDavies @Hesamation
Now this is a bit better answer. I will look into it and come back with a better argument if i find something interesting.
Replying to @arpit_bhayani
If im bad then the whole world is bad ahh logic
Replying to @OscarMDavies @Hesamation
No i think it is. And you cannot prove me wrong because apparently there is no definition of consciousness .
Replying to @OscarMDavies @Hesamation
I think AI and puddle of water is conscious. Now prove me wrong using facts instead of diverting the argument.
Replying to @OscarMDavies @Hesamation
Im asking you, you said so confidently it isn't then there must be some reasoning which we can use to establish if other things are or not
Replying to @OscarMDavies @Hesamation
How is puddle of water not conscious?
Boldbug retweeted
if you have a qwen3.5 4b around, please try steering neurons L14 N8949 +1 and L13 N7956 -1
now you have evil qwen
recipe: dose × median(‖resid‖ leaving layer L, tokens 1:) / ‖W_down[:, n]‖` at the down_proj at every input
Replying to @CtrlAltDwayne
Thats what people told him in 80s too when he was working on neural networks , they told him its not possible and is stupid but he kept working and that neural networks shaped the AI today. He is not new to this game where people call him wrong and think they are smarter
Replying to @OscarMDavies @Hesamation
Thats what people thought of him in 70s too , they told him neural networks is a bad idea and it will never work but he kept working and it worked. He is not new to this where people call him he is wrong







