HN Explorer

Investors Serious About Application of Solomonoff Induction to Model Selection?

2 points by jabowery ↗ HN
I'd like to contact investors who are serious about applying Solomonoff Induction. By "serious" I mean they avoid these 2 fallacies about Solomonoff Induction:

Fallacy 1) That its greatest importance is for artificial intelligence. Fallacy 2) That it is just another information criterion for model selection.

Perhaps later I'll be interested in arguing about why these are fallacies, but given that the Hutter Prize has been out there for over 15 years and the arguments have been presented over and over again, I'm more interested in finding like minds among investors.

9 comments

[ 3.3 ms ] story [ 25.0 ms ] thread
koyanisqatsi
Investors don't care what technology you are using and for what purpose (as long as it is legal), they only care that you make more money than they gave you initially.

Your request won't get any responses because your pitch does not address a VC audience. The set of VCs and the set of people who know about AIXI/Solomon induction have an empty intersection. You're not gonna find a VC that knows anything about those terms.

jabowery
The flip side of that wisdom is that investors don't invest in technologies, the markets for which they know nothing about. See "technical market research".
koyanisqatsi
My point is your pitch is falling on deaf ears, there is no VC that understands what you're talking about. VCs don't invest in autistic savants, they invest in people that are good at explaining an exploitable/profitable business opportunity.
jabowery
Yes, I know what your point is. I'm just wondering if the distribution of "VCs" has a fatter tail than you think. The very name of this website, "ycombinator" is rather "on the spectrum" but it is obviously less so now than it was, say, back in the early 80s when Haskell Curry signed my sigplan proceedings. Likewise, back in 2006 when Marcus sponsored the Hutter Prize, it was rather "autistic" to think there would be anyone who understood what he was talking about. Then his "autistic" PhD students founded DeepMind and everyone went nuts about AI. I could cite dozens of examples of the way distributions shift in directions that seemed at one time to be only for "autistic savants".
koyanisqatsi
People here don't know anything about AIXI/Solomonoff induction either but you can go ahead and site the examples. Maybe they will convince some VC to finance whatever business plan you have for making lots of money.
jabowery
Thank you for your medical diagnosis of my speech patterns. But the fact that you conflate the 2 decade old AIXI with the 5 decade old Solomonoff Induction despite my attempt to filter out ignoramuses with the 2 fallacies (neither of which mention AIXI and one of which specifically singles out AI/AGI for elimination), I'm afraid you've just been filtered, along with your medical diagnosis.
koyanisqatsi
That's fine. Good luck with your endeavor but I still think you should contact some friends and family. If that's not possible then a helpline might also be beneficial: https://sczaction.org/helpline/ (toll-free number: 800-493-2094).

We can also continue this thread if you want but you'll have to make more coherent points about what exactly you're trying to achieve with Solomonoff induction. Most of the research on AIXI(tl) is pretty much complete. Whatever could be recovered from computable distributions and agents that learn properties of that distribution to maximize some kind of objective has already been mostly figured out by Hutter. The theory is complete so unless you have some other ideas I don't think there is anything worthwhile left to research with Solomonoff induction and computational agents based on that formalism.

jabowery
"Tendencies of physicians in training to be overconfident have to be taken into consideration to ensure the appropriate degree of supervision and feedback."

https://en.wikipedia.org/wiki/Dunning%E2%80%93Kruger_effect

I don't know that my diagnosis is correct, but it certainly seems to be the case that your continual referral back to AIXI despite it being excluded from consideration in my original post and then re-excluded in my most recent comment indicates that your reading comprehension (including my "speech patterns") isn't nearly what you think it is. Of course, another explanation is that you are simply a troll, but that is a decreasingly likely explanation.

koyanisqatsi
By the way, your speech patterns indicate schizophrenia (rambling and meandering speech that doesn't really make any point). If you have family and friends I recommend you get in touch with them and ask for help. They could get you some prescription medication that might help with your symptoms. [1]

1: https://www.drugs.com/condition/schizophrenia.html