Deepmind is actually working on an AI that improve performances of low level programs. It started with improving sorting algorithm.
It’s an RL algorithm.
Main issue is that everything takes time, and expectations on current AI are artificially inflated.
It will reach the point most are discussing now, it’ll simply take a bit longer than people expect
Death_Equity@lemmy.world 1 year ago
Wait, has anybody bothered to ask AI how to fix itself? How much Avocado testing does it do? Can AI pull itself up by its own boot partition, or does it expect the administrator to just give it everything?
wizardbeard@lemmy.dbzer0.com 1 year ago
Really says something that none of your responses yet seem to have caught that this was a joke.
FaceDeer@kbin.social 1 year ago
OP might have been intending it as a joke, but self-improvement is a very real subject of AI research so if that's the case he accidentally said something about a serious topic.
Buddahriffic@lemmy.world 1 year ago
It’s an essential part of the idea of the technological singularity. An AI iterates itself and the systems it runs on, becoming more efficient, powerful, and effective at a rate that makes all of human progress up to that point look like nothing.
Death_Equity@lemmy.world 1 year ago
The upvotes vs comments shows the vocal minority is just doing vocal minority things.
vrighter@discuss.tchncs.de 1 year ago
if we don’t know, it doesn’t know.
If we know, but there’s no public text about it, it doesn’t know either.
it is trained off of stuff that has already been written, and trained to emulate the statistical properties of those words. It cannot and will not tell us anything new
FaceDeer@kbin.social 1 year ago
That's not true. These models aren't just regurgitating text that they were trained on. They learn the patterns and concepts in that text, and they're able to use those to infer things that weren't explicitly present in the training data.
I read recently about some researchers who were experimenting with ChatGPT's ability to do basic arithmetic. It's not great at it, but it's definitely figured out some techniques that allow it to answer math problems that were not in its training set. It gets them wrong sometimes, but it's like a human doing math in its head rather than a calculator using rigorous algorithms so that's to be expected.
vrighter@discuss.tchncs.de 1 year ago
they learn statistical correlations between words. given the last 5000 (or however large the context is) words, and absolutely no other information besides that, what is the most likely word to appear next? It’s a glorified order 5000 markov chain.
The reason it can “do” some math is that there are tons of examples in the training set using small numbers usually used as examples. it can do basic arithmetic because it has seen “2+2=4” and other examples with simple numbers like that. The studies used test basic arithmetic. The same things that it had millions of pre-worked examples of. And it still gets those wrong, with astonishing frequency. those studies aren’t talking about asking it “what is the square root of pi” or stuff like that. but stuff such as “is 7 greater than 4?”, “what is 10 + 3?”, “is 97 prime?” stuff it has most definitely seen the answers to. ask it about some large prime, and it’ll nay no, and be probably right, because most numbers are composite
discodoubloon@kbin.social 1 year ago
It doesn’t “know” anything. It can’t solve that problem. It’s trained on humans so it’s limited to what we have written down.
I love ChatGPT but if it’s creative it’s because you asked it the right questions and found an oblique answer yourself.
Buffaloaf@lemmy.world 1 year ago
I asked Bard how ChatGPT can fix itself, here’s what it said:
ChatGPT can fix itself in a number of ways, including:
Retraining on a larger dataset. ChatGPT is trained on a massive dataset of text and code, but it can always be retrained on a larger dataset. This would help ChatGPT to learn new things and improve its performance.
Using a different algorithm. ChatGPT is currently trained using the GPT-3 algorithm, but there are other algorithms that could be used. For example, ChatGPT could be trained using the Megatron-Turing NLG algorithm, which is one of the most powerful language models in the world.
Using a combination of algorithms. ChatGPT could also be trained using a combination of algorithms. This would allow ChatGPT to benefit from the strengths of different algorithms.
Using a feedback loop. ChatGPT could be used to generate text, and then this text could be used to train ChatGPT. This would allow ChatGPT to learn from its own mistakes and improve its performance over time.
Using human feedback. ChatGPT could also be used to generate text, and then this text could be reviewed by humans. The human feedback could then be used to improve ChatGPT’s performance.
chaogomu@kbin.social 1 year ago
The feedback loop is already happening, and is called model collapse.
It's not a good thing.
FaceDeer@kbin.social 1 year ago
The full suggestion includes "This would allow ChatGPT to learn from its own mistakes", which implies that the text it generated would be evaluated and curated before being sent back into it for training. That, as well as including non-AI-generated text along with the AI generated stuff, should stop model collapse.
Model collapse is basically inbreeding, with similar causes and similar solutions. A little inbreeding is not inherently bad, indeed it's used frequently when you're trying to breed an organism to have specific desirable characteristics.
lagomorphlecture@lemm.ee 1 year ago
“Using a feedback loop. ChatGPT could be used to generate text, and then this text could be used to train ChatGPT. This would allow ChatGPT to learn from its own mistakes and improve its performance over time.”
So basically create its own Fox News and see how that goes.
vrighter@discuss.tchncs.de 1 year ago
this is widely known to very quickly destroy your model
FaceDeer@kbin.social 1 year ago
If having an AI tell researchers that they should base its next iteration off of Megatron isn't the plot of a Michael Bay Transformers movie already, it should have been.
Zeth0s@lemmy.world 1 year ago
It’s working on it. It’s just a pretty difficult task to be better than 50 years of optimization by human computer scientists www.nature.com/articles/d41586-023-01883-4