It's exactly at the level I thought was communicated by the title and introduction.
"Human level competitive", "solidly amateur-level human performance", "beat 100% of beginners and 55% of intermediate players". That robot would definitely win some games in your local club league, except that it doesn't serve, and unless it's cheating in ways the announcement glosses over like extra cameras - DeepMind have some history here so I reserve the right to be skeptical.
The only thing I'd take issue with in the abstract is "Table tennis... requires human players to undergo years of training to achieve an advanced level of proficiency." While that sentence is true, it's irrelevant to this robot since this robot only plays at intermediate proficiency, a level reachable by a moderately athletic human with some practice.
By contrast, the AlphaGo [0] AlphaZero [1] and AlphaStar [2] papers claim "mastery", "superhuman", "world champion level", "Grandmaster-level", "human professional" ability - all defensible claims given their performance and match conditions in the respective games.
> That robot would definitely win some games in your local club league
Definitely not. If you go beyond the cherry-picked videos where some longer sequences happened, the longer match videos reveal how bad the robot is. It makes really bad mistakes and loses most points against players not even on intermediate player in any local club.
Yeah, looking it play makes me thinks it has a level comparable to mine, that is the level of someone that enjoys playing table tennis with friends and family members a every other year. Not at all the level you'd see in clubs, even among low-ranked people.
I'd describe the robot's level as "good for outdoor table tennis".
There are pretty much too distinct classes of players. Those that occasionally play for fun, typically at stone tables found in parks and open-air baths.
And then there are those that play and train at least once a week in indoor halls with wooden tables, and often try to learn proper stroke techniques, and often participate in leagues.
The robot is pretty good fit for the first category, and that's already a pretty impressive achievement.
In the second category, it'd lose to anybody playing for more than a year or two, so it would be on par with the lowest tier players there.
My local club is full of (mostly older) players who play once a week for a few hours. They don't train outside of this, but they play with proper equipment, sometimes play leagues, sometimes play a few strokes well, and beat anyone who just plays casually, apart from the occasional excellent tennis player who can transfer just enough skills to be competitive. But they also make lots of unforced errors and don't have good technique on all strokes.
The robot looks like it would be competitive with most of those players. Maybe my club is uniquely weak.
The AlphaZero paper claimed it was vastly superior to Stockfish, the top open source engine, based on a 100-game match against Stockfish. It turned out Stockfish was running with way less compute. It's not an apples to apples comparison between CPU and GPU, but IIRC there were orders of magnitude difference in the hardware cost and power budget. Additionally, they used a build of Stockfish that was tuned based on having access to opening books and endgame tablebases, but didn't give it those resources in the match.
The original AlphaStar announcement was also based on having serious advantages over its human opponents: it got a feed of the whole map, where humans could only view a section at a time, and the ability to perform an unrealistic number of actions per minute.
The equivalent in table tennis? Maybe having an additional high speed camera on the other side of the table, or a sensor in the opponent's bat. Actually, why is the opponent playing with a non-standard bat with two black rubbers? Presumably that's an optimization where the robot's computer vision has been tuned only for a black bat. But if that's so, it means none of the opponents got to use their own equipment, they used a bat which was unfamiliar and perhaps chosen to be easy for the robot to play against.
I could concede it as "lower intermediate", but the span is huge. I don't think it can beat an upper beginner consistently. It all depends on what ELO you consider intermediate.
But the company that figures out platooning can also work on self-driving, or can partner with or sell itself to the company that does figure out self-driving.
Working on platooning - assuming it's a more or less viable business idea on its own - doesn't need to be a distraction that prevents anyone from developing fully autonomous trucks.
According to Wikipedia they aired music by Black musicians from day 1, with the Specials among others in their first program [0].
They were criticized for not having enough black acts. That's a reasonable criticism, but let's not make it sound like some kind of apartheid. They made a commercial decision about what genres to focused on, rather than something racially motivated. They didn't air many videos by country singers or classical violinists either.
Wikipedia’s article whitewashes the actual history. We were watching MTV and smoking weed in those Reagan’s America days.
—
In fairness the US music industry had the race music chart which became the R&B chart to keep black musicians off the pop chart and Elvis’s controversy was singing black music…and consequently being played on white radio stations to white kids.
Lots of white artists were repackaging black recordings for segregated radio play in the 40s and 50s. It was routine in that era for any popular song to be covered by many artists within the same year, so it wasn't entirely insidious but there was a definite whitewashing going on with more than just Elvis. Georgia Gibbs is a notable case. Elvis' controversy was more the "sexualized" dancing which was among the things sanitized out of the covers.
Most of the benefit of the Shuttle program, and manned spaceflight in general, has come from R and D on the launch process, or from the prestige and bragging rights of being able to launch humans into space. So once they're up there, you're getting your money's worth (or not) no matter what they do, you may as well do something cool like recover a historic satellite.
There is no "the number of teams", because this league has a promotion/relegation system. There are 20 teams in the league at any point in time, but 150 or so professional clubs and tens of thousands of others who participate in the league pyramid and have at least a theoretical chance of promotion and ultimately winning the premier league.
There's a fair bit of churn in these numbers: 51 clubs in total have been in the premier league in the period of interest (the last 33 years).
After some small threshold, I think the number of clubs doesn't matter. You could get the same result if the top 100 or all 40,000 clubs played in the same league every year, ignoring the minor scheduling problem this would cause. Resources are distributed approximately in a power law, as you suggest. What matters is the level of inequality near the top, which is apparently such that each team has approximately phi times the resources (measured over a long period) of the team below.
The question is self-answering as soon as you read the first two sentences though.
> Columbia...has an endowment of roughly $15bn. Mr Trump’s administration withheld a mere $400m in federal funding.
With the best investing in the world, that $15bn might throw off 1 billion a year in perpetuity. $400m (a year) is a very serious chunk of the university's budget.
Exactly... Scaling the numbers down: It's as if a person has $1.5M net worth, and their investments produce $100K per year. They are also simply being handed $40K per year from someone they disagree with, but who otherwise reliably provides that income. Are they just going to turn that money down because of this ethical disagreement? A lot of people wouldn't.
Or alternatively, their investments from one account produce $100K per year, their investments from another account (non-Federal grants) produce an unknown amount, and they have a job (tuition payments) that produces another unknown amount. How significant is 40% of the 100K?
We don't know unless we fill in the unknown numbers. Knowing that the amount of federal aid being removed is 40% of an estimate of the amount produced by one source (the endowment) isn't enough information to answer the question. The right question is what percentage of their budget this represents.
From what I can tell, Harvard's actual annual budget is about $6.5B (https://www.harvardmagazine.com/2024/10/financial-report-fis...). A $400M shortfall is thus about 6% of their annual budget. Significant, but also something they could probably cover for the next decade or two by drawing down their endowment until they adjust.
reply