jerlendds

I completely agree. I'm betting on physical learning systems via reservoir computing personally. Will be going back to school to study nanotechnology soon to pursue this formally in addition to some experiments Ill be funding and running on my own dime as well. Have you ever seen steel ball bearings submerged in castor oil? If you apply an electrical current to that what do you think will happen? The most fascinating thing occurs, the ball bearings self organize into a network that can even display properties of hebbian learning if set up correctly! I suspect experiments such as these will eventually even raise the bigger question of, what is life actually? Another way to think about the potential of this area of technology is to think of a biological synapse, its about 1 micron in size right? Well, how many "neural atoms" can we fit in that space? 1000x1000x1000!! Its marvelous how much space there is when you shrink things down. Ill even go so far as to speculate that to create genuine superintelligence, youll need this technology Ill be working on to mature and form into some.new form of stochastic processor/computer

Yes, I havent seen research on this tactic specifically for language models but for generative image models you can find research thatindicates you get far more variety and diversity in the images returned when suffixing the context with "noisy context" such as random letters or something else unrelated that wont "confuse" it or make it go off the rails

Found this interesting paper today while searching around the keywords "attractor language networks". This part I found especially interesting:

*Attractor Models outperform existing models across two regimes, large-scale language-model pretraining and reasoning with tiny models.*

Im usually on Firefox and I haven't run into this. But I also spent the past 2 days building a Knitsail VM solver in Rust for pulling Google Search results. Works nicely, I gave chatgpt pro (6) a minified JS bundle, and some variables and entries into the VM and told it to reconstruct the VM in Rust. Only took a couple hours to get a zip with a solver I could plug into my crawler, made a few mistakes but codex fixed those up with minimal guidance. No more Google captchas for me :)

I unfortunately live in Alberta and I have to say Smith seems decently smart. Which is not to say I agree with or would vote for her but that shes very capable of getting things she wants. Seeing Alberta pop up on HN so often is disheartening. I hope she gets voted out soon or I just might have to move