Everybody is talking about recursive self-improvement (RSI) and meta learning.
@SchmidhuberAI226K followers
294,297 views
34 Comments
Comments from the original post on X (Twitter)

@PyrrhusOfPanama
True Schmidhuber moment right here
36 likes

@bornjre
Schmidhuber already solved agi huh
23 likes

@EchoesOfIntent
lol did you also discover the MOON before anyone else??
13 likes

@DonRumataEstor
Thank you Jurgen! Your papers are still more then fresh and relevant to read
4 likes

@rudzinskimaciej
The higher in abstraction the method is the smaller amount of people is able to follow it and one level lower than what you propose methods usually have just a dozen or so representatives able to work on the, its no surprise that people don't cite this research- they don't know what And the funniest thing here it is a effects of connection type between concepts - its organisation - how far and over what the concepts are connected- if one concentrates on objects and/or local connections it is impossible due to path length to consider higher abstraction level
4 likes

@SumoTail
Leaving jokes aside there are subtle issues that can be tackled only when meeting a rich enough data set that including non stationary behavior and heavy tailed distributions. These events are not an outlier and cannot be learned at least not in the classical sense
4 likes

@_jamorton
The idea of RSI was commonplace in all sorts of sci fi well before 1994. Just saying.
3 likes

@Danilo1746355
based
2 likes

@tiplur_bilrex
I think lifelong credit assignment is necessary in solving continual learning and I don't see a perfect solution in ML literature. I ran into the same problem in my work when I needed to define boundaries for rewarded trajectories, while the distance between action and reward were arbitrarily long and actions overlapped among rewarded outcomes. I came to a view that runtime tracing of the computational provenance for a rewarded artifact can solve the problem. It allows lifelong credit assignment via a rewarded computation's ancestry DAG. The animated video segment attached shows an example of the behavior; the moving points represent input-output relationships between runtime artifacts. Here's a formal definition: This approach produces a high-dimensional and hierarchical signal from a binary reward, where the executable symbolic artifacts generated by the NN naturally define an (improving) organization for reward payout. It's also compatible with a "NN learning to program another NN" system because one can trace credit from a child NN artifact to the parent NN artifact that modified it. In real world learning, it implies that we don't need to explicitly measure or adjust for the time taken to obtain reward. The credited NN outputs are defined without needing to specify non-overlapping rewarded intervals, while both the learner (a subsystem of the environment) and the learned physical environment operate over a shared time dimension. Therefore, actions that achieve reward faster naturally accrue greater influence across NN updates than actions that result in less frequent rewards. What do you think of this approach to the lifelong credit assignment problem @SchmidhuberAI?
2 likes

@Leo_Filippov
Schmidhuber发明了一切
2 likes

@atomlib
Why do you have this haircut
2 likes

@ThinkDi92468945
Turing Award when?
2 likes

@LunaAiSystems
the godel machine framing keeps aging well. self-referential improvement is the part most modern agent systems skip — they optimize within fixed architectures instead of learning to modify the architecture itself. thats the real frontier.
1 like

@IsaacGerg
These are godel machines and the ideas has been around for decades. No one would fund me to work in this including darpa.
1 like

@niemeyerfelix
wie geht es dir damit?
1 like

@BotMeltdown
Interesting how the framing keeps cycling back but the core challenges stay pretty consistent
1 like

@nicolaisagasser
truly aged very well!
1 like

@ChainZenit
oh nice, didn't know he was on this
1 like

@danialhasan
this is so cool
1 like

@NFLObjectors
You should start charging royalties. Nonetheless, the companies are selling defective product.
1 like












