Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Go grandmaster Shin defeats AI KataGo with a two-stone handicap

kedglobal.com

Post reply on HN
Print view View original

121–130 of 187 posts

Re: Go grandmaster Shin defeats AI KataGo with a two-stone handicap

#121

Post by dist-epoch »

harshreality wrote: post #56
afthonos wrote: post #24

Earlier quoted context omitted.

Important to note that KataGo was double-handicapped. 20 seconds per move maximum; it couldn’t read deep. Against an amateur, it doesn’t matter, but against a historically strong pro it matters a lot.

...on a 4x 3090 rig. The game ran 299 moves, giving katago 100 minutes if it exhausted time on each move (which must be the optimal strategy under that time control). Shin used about 205 minutes, over twice as much time and of course had leeway to spend more time on difficult moves. Based on the youtube video, it looks like katago was only using 16 seconds per move, is that right? https://www.youtube.com/watch?v=-86z…

Considering the original AlphaGo ran on a full Google TPU rack, and here KataGo seems to run on a $10k computer, and won with 2 stones handicap, this is showing just how much advance there was in computer go

Re: Go grandmaster Shin defeats AI KataGo with a two-stone handicap

#123

Post by DiogenesKynikos »

snakeboy wrote: post #101
DiogenesKynikos wrote: post #71

Earlier quoted context omitted.

You can't compare Elo ratings over long stretches of time, period. Ratings drift over time, based on the total population of people competing. I think the most accurate way to view Elo ratings is as a measure of skill vs. the average rated player. If you want to compare Magnus Carlsen's peak rating of 2882 in the year 2014 to Garry Kasparov's peak rating of 2851 in the year 1999, you have to know how strong the total…

> If you want to compare Magnus Carlsen's peak rating of 2882 in the year 2014 to Garry Kasparov's peak rating of 2851 in the year 1999, you have to know how strong the total pool of players (including all the amateurs who compete at lower levels) was in the year 2014 vs. 1999. I imagine that FIDE has all of this data somewhere, right? They don't publish more in-depth distributional analyses of players somewhere?

The distribution of Elo ratings will not tell you how strong the average player is in an absolute sense.

Elo ratings measure differences in skill between different players. A player rated 400 points above another player will win 90% of the time. Only rating differences are meaningful. Absolute ratings aren't.

Re: Go grandmaster Shin defeats AI KataGo with a two-stone handicap

#124

Post by DiogenesKynikos »

hyperpape wrote: post #118
DiogenesKynikos wrote: post #71

Earlier quoted context omitted.

You can't compare Elo ratings over long stretches of time, period. Ratings drift over time, based on the total population of people competing. I think the most accurate way to view Elo ratings is as a measure of skill vs. the average rated player. If you want to compare Magnus Carlsen's peak rating of 2882 in the year 2014 to Garry Kasparov's peak rating of 2851 in the year 1999, you have to know how strong the total…

> You can't compare Elo ratings over long stretches of time, period. I agree that you cannot do it reliably, in principle. However, Bobby Fischer peaked at 2785, and Gary Kasparov peaked at 2851. These are not far from what informed observers suggest--maybe 50 or 100 points off. They are well into super-grandmaster territory. Kasparov would be 1st today, Fischer would be 4th. But on goratings.org, the top player of t…

I agree that the drift in chess Elo ratings is slow enough that we can say Bobby Fischer at his peak would still be a strong grandmaster today (if he were given some time to study developments in opening theory). But I don't think we can say whether he would land at 2700 or 2800 in today's Elo scale.

Re: Go grandmaster Shin defeats AI KataGo with a two-stone handicap

#125

Post by criddell »

edh649 wrote: post #115
qnpnpmqppnp wrote: post #114

Earlier quoted context omitted.

It's not clear from the revised title either though. In fact I found it even more confusing. The issue is the ambiguity of the wording "with a two-stone handicap", not where it's located in the sentence.

I would probably phrase it as 'Go grandmaster Shin defeats two-stone-handicapped AI KataGo'

Are there ads on the page? If so, let’s A/B test that along with “Grandmaster Shin Savagely Beats Handicapped Opponent”.

Re: Go grandmaster Shin defeats AI KataGo with a two-stone handicap

#126

Post by Sharlin »

nswango wrote: post #92
teleforce wrote: post #66

Earlier quoted context omitted.

>Go grandmaster Shin defeats AI KataGo with a two-stone handicap English is not my first language but for clarity perhaps the title should be: Go grandmaster Shin with a two-stone handicap defeats AI KataGo

Idiomatically a handicap is a disadvantage not an advantage. So if Shin had two extra stones, KataGo had a two stone handicap.

Yes, but the title has an ambiguous parse (a shift-reduce conflict):

X defeats (Y with Z)

or

(X defeats Y) with Z

with the latter usually understood as meaning X has Z, as far as I know.

Re: Go grandmaster Shin defeats AI KataGo with a two-stone handicap

#127

Post by bawolff »

teleforce wrote: post #66
zelphirkalt wrote: post #32

Earlier quoted context omitted.

I read this comment before looking at the article and thought that the grandmaster beat the AI even giving the AI 2 stones. Too bad. But this way around is of course more realistic. And of course you would need to take into consideration the scale of go ratings and chess ratings when making that comparison. With top chess ratings being around 2800, being 1000 less than the top go ratings, one would have to apply a fa…

>Go grandmaster Shin defeats AI KataGo with a two-stone handicap English is not my first language but for clarity perhaps the title should be: Go grandmaster Shin with a two-stone handicap defeats AI KataGo

fwiw, as a native speaker, your revised version sounds wrong. I'm terrible at grammer, but i think it's because when you put the "with" early in the sentence, it acts as a preposition modifying the noun, where later in the sentence it acts as an adverbial phrase modifying the verb defeat. The handicap is describing the manner of the defeat and not a trait of the grandmaster, so the with has to go at the end of the sentence.

Or that at least is my guess as to why it sounds wrong.

Re: Go grandmaster Shin defeats AI KataGo with a two-stone handicap

#128

Post by monster_truck »

rao-v wrote: post #5

It’s worth understanding that Shin Jinse has been significantly stronger than his nearest human opponents for a while now, more so than Magnus was even at his very peak. In go ELO like scoring he’s something like 120 points over the next strongest player. No other player has ever broken a 3800 rating let alone 3850. Ke Jie (the previous long time champion) peaked at 3755. Shin Jinseo’s strength graph is the most absu…

This was only running on 4x3090s man. The gap is far, far wider than you think. 8 5090s or 6000s and at least as many extra dedicated to doing nothing but running disgusting amounts of monte carlo in parallel from anything resembling a good choice (fuck it check some bad ones too) would lay him to waste.

I am going to go out on a limb and say part of it is a matter of respect, and part "lets not discourage and scare the shit out of anyone who knows even a little about Go"

A long time ago I ported a Go game to the iPhone for a job, the only way to control difficulty was to limit the amount of time it could spend monte carloing. On the iPhone 4, "Hard" would take 20-30 seconds a turn and drain your battery. I learned the game as I was making the app, got into single digits vs humans years after that. When the iPhone 5S came out it was capable of doing so many more iterations a second that even the easiest difficulty destroyed me until I spent enough time figuring out which moves created the worst spaces for it to search, which isn't really playing go anymore it's more like mining bitcoin by hand.

E: 4x3090 tops out at ~1.4k nnEvals/s. 4x5090 is 3.2x. 8xRTX 6000 something like 7x.

Re: Go grandmaster Shin defeats AI KataGo with a two-stone handicap

#129

Post by japanoise »

thataccount wrote: post #53

I don't know what the fascination with these AI versus human tournaments is. I'm old enough to remember the whole "Deep Blue" vs Kasparov exhibition, and I didn't really understand the fascination with all that either. That humans can make sufficiently strong calculators has never been a dispute in my mind. If the human wins over the calculator, good, but if the calculator wins, okay. What does that tell us exactly?…

It's all narrative. Abstract strategy games with perfect information (like chess and go) look at a casual glance like they should be difficult for computers, but in fact they're rather ideal. Before AlphaGo, belligerent go players used to smugly dismiss chess as a 'solved game' (not what that means) because chess engines have been better than the best humans for years.

Re: Go grandmaster Shin defeats AI KataGo with a two-stone handicap

#130

Post by ziofill »

zelphirkalt wrote: post #32
rao-v wrote: post #5

It’s worth understanding that Shin Jinse has been significantly stronger than his nearest human opponents for a while now, more so than Magnus was even at his very peak. In go ELO like scoring he’s something like 120 points over the next strongest player. No other player has ever broken a 3800 rating let alone 3850. Ke Jie (the previous long time champion) peaked at 3755. Shin Jinseo’s strength graph is the most absu…

I read this comment before looking at the article and thought that the grandmaster beat the AI even giving the AI 2 stones. Too bad. But this way around is of course more realistic. And of course you would need to take into consideration the scale of go ratings and chess ratings when making that comparison. With top chess ratings being around 2800, being 1000 less than the top go ratings, one would have to apply a fa…

I don’t think so: the ELO rating difference is what matters, e.g. a 1000 player vs an 800 player has the same win probability as a 2800 vs a 2600.
Post reply on HN