My failed attempt to change TCEC NN clone rules

[MikeB]

Nah, if they wanted that you'd have been asked about what was your favorite movie, and if you disliked some parts of it and stuff like that, some creative process, not force you to watch some movie and tell what it was about.

The problem with a movie summary is that there's some expected standard, and kids are expected to follow it as close as possible. The professor has watched the movie and has interpreted what's it about, and kids are judged about how close they can be to this summary on the professor's head. It doesn't allow a different interpretation of the movie.

Also, it'll mostly focus on good orthography and grammar, the professor will be quick to point out any mistake, as if how things were written was more important than what was written. Even though outside school these abilities aren't useful in life.

I really want to ask anybody reading this if improving their writing skills has helped them in their life. In my experience, as someone that had to learn English as a second language by myself (because my country is the definition of failure when trying to do it, with most of my teachers having a poorer English than me), comparing what I'm typing now to what I used to type back in 2001, which would have 3 or more mistakes per paragraph, and stuff like "thanks for read", the only benefit whatsoever I've seen is fewer people correcting me. That's all. From the get-go I was able to communicate, people correcting me were able to do so because they already knew what I wanted to say, and the "correct" way of saying it.

The only thing people with high writing skills can do is correcting mistakes in what other people say, the amount of misunderstandings remain about the same. It's yet another example of school teaching you something that is only useful in school.

Good writing helps everywhere. It helps at work whether in business communication or writing documentation. The longer the composition, the more important the quality of your writing. If your writing is poor, people's opinion of you will reflect that. It can make the difference between getting a promotion, a pay bonus or a pay raise. It's a reflection on how much you care about the quality of your work, which includes writing. Words fitly written can make all the difference in convincing people regarding important issues.

+1

[Ovyron]

Words fitly written can make all the difference in convincing people regarding important issues.

I've learned that the hard way. But my best lesson was that convincing such people of anything is mostly a waste of time. The most brilliant children I've known didn't know how to write or read yet, and the horror was meeting them years later only to discover that while they were much better at forming sentences and expressing ideas, their brilliancy had gone away. They also behaved a lot more like little robots, as if life was sucked off from them by education.

[hgm]

I think that we should then stop looking at an engine's author, so if an author creates 6 different engines from scratch and all of them are different, we should treat them as different entities and allow them all. Conversely, if 2 authors create two independent engines from scratch but they end up playing the same, we have no reason to have them both in.

This has always been my attitude to engine tournaments. I should add that the entry of two same-author engines in said CSVN tourney (which was not an official championship, btw) was mostly because of my pushing for allowing micro-Max to participate. Joker and micro-Max were entirely different programs, not sharing a single line of code, and micro-Max was at least 400 Elo weaker. So I saw no reason why the participation of Joker should disqualify micro-Max.

The argument that this makes the tournament vulnerable to cheating of the type Gian-Carlo suggests doesn't seem very convincing to me. Sure, it would be possible to enter two copies of your strongest engine, and intentially let the one that has the best prospects win when they play each other. But it is just as easy to do that anyway, using a front to claim the copy was his engine, enter it in his own name, and play the same game. This is actually easier, as entering two engines in your own name immediately attracts scrutiny.

Of course it makes a large difference whether a computer-chess event is intended to be a competition between programs or between programmers.

[Madeleine Birchfield]

Today after my post Anton wrote me that my concern is not forgotten and there’s tremendous work going on to fix NN clone rules (for more than 6 months already!).

Even if I believed that (which I don’t), I still would think it would be done very wrongly. I did write a lot of input, I really spent 4 hours almost every evening for more than a week coming up with pros and cons. Don’t I deserve any feedback? Shouldn’t be I included into the discussion? Shouldn’t the discussion be public after all?

No, it’s “be sure that rules committee will review your input thoroughly and will take into account in the new version of rules, and please keep it TOP SECRET”. And new rules/competitors are usually published at the last day and very publicly when there’s too late to change anything.

I don’t know who “rules committee” is, but what they came up with last time was just silly.
I suspect last time they also got “input to review” from me, although I’m not sure.
It was during DeusX incident. I chatted about that with Anton and told that what ASilver did is he took scripts from Lc0 project and trained the net, and the engine itself is Lc0 too.

What was the resulting rule? You all know:

NN-based engine consists of 3 parts:
1. Neural network.
2. Engine.
3. Training script.
You need 2 of 3 to be unique to be unique.

It’s so detached from reality! What is “training script” doing here? I was really perplexed. Who came up with those “2 of 3”? Training script is something that can be written in 1-2 hours (and I’m surprised no one did that to work around TCEC rules), it’s really very minor piece of work compared to other (others are very ambiguous too, I’ll post about them too a bit later).


If “rules committee” is working the same way (reviewing inputs and generating rules without public discussion), it will be again same bad.

Huh, there used to be guidelines for Leela like engines using deep CNNs at TCEC like there is for NNUE engines right now. When did those get removed from TCEC?