domhudson

Thanks! Your diagnosis was correct - it was still calculating complexity for a move normally ignoring whether it was forced or not.

Resolved :) Here's a reprocess of your game: https://chesscheaterdetector.com/analysis/7aviGW

Might update suspicion to always be 0 when it's forced too...

It actually looks like your game did have engine-assistance right? So might need to use this as a false-negative case also.

Thanks for trying it! That's interesting - please can you share the analysis link here if you still have it?

If this is a marketing stunt to use such a bad font; honestly, I'm impressed.

Really cool! Are you able to add an indicator showing which direction you're travelling in? It's quite confusing to start due to all the effects.

I also recommend a banner that says it doesn't work on mobile as it was quite confusing to me as to whether it was working or not.

It's not my project, but here you are! https://github.com/xevrion/breakscale

Looks really very nice. I built an interface for ML active learning in the terminal a while back. Wish this had existed at the time.

This is incredible! Are there other big players in this space (freezing models to silicon)?

Interesting point. Yeah, I agree timing should be a strong signal. It seems like there are a few ways it could be included:

- Measure a correlation between position complexity and time spent per move. You would expect a good move to take longer to calculate in complex positions.

- Move timing consistency, humans are all over the place with timing, whereas cheaters often move regularly.

- Long pause, then strong play. If a cheater starts cheating half way through a game, then there could be a transition period where they first enter the position into the engine.

Instructables.com used to be very much like this. The community was built around people posting guides for building DIY projects, with some of them being extremely impressive and creative.

I just took a look, and it appears to have changed now though. At least, from the logged out perspective.

By Philip Su

You don't have to cycle it. You also don't need to load it (a marketing ploy to get you to buy more).

You can just take 3-5g daily.

He finished his PhD two years ago, and worked at GDM since. Very unlikely he'll have saved 7 figures in that time, let alone 8.

Do you have any thoughts on if, or how, you'll adjust once AI writing has made it into new long-form published works?

Hi thanks for your interest. I have added a GPL v3 license now.

Thanks

I have tried plasticity (even submitted a PR*) before putting together this repo but found it horrendously slow in comparison. It really does depend though; as plasticity utilise an in-mem cache if you're querying on many similar words repeatedly, that is likely to be faster.

EDIT: sorry it wasn't a PR but an issue