GPT-6 ASTRA vs CLAUDE FABLE 5.1 (INSANE CHESS MATCH)



Get My New Intermediate Book Out NOW:

BOOK EVENTS NYC:

EUROPE TOUR 2026 TICKETS:

Want to SKYROCKET your chess elo? Try Chessly:

➡️ My book in the UK and Europe:
➡️ Mein Buch auf Deutsch:
➡️ Mi libro en Español:
➡️ Mon livre en français:
➡️ Il mio libro in italiano:
➡️ Το βιβλίο μου στα ελληνικά:
➡️ My book in ALL OTHER LANGUAGES:

➡️ Start Playing Chess FOR FREE:

➡️ Enjoy my videos? Donate Here :

Email me your games: gothamletters@gmail.com
Business and Speaking Inquiries: Info@apollomasters.de

⭐️ Follow Me If You Are Amazing:
➡️ FACEBOOK:
➡️ SNAP:

➡️ INSTAGRAM:
➡️ TWITCH:
➡️ TIKTOK:
➡️ TWITTER:
➡️ GOTHAM DISCORD:

➡️ THUMBNAILS by :

source

29 Comments

  1. As a software engineer, you really have to check what commands it used to fully know if it did use a chess engine, i've been using astra and fable and they are great models. But the shift from doing so many illegal moves from previous models to suddenly only a single illegal move could imply that they recently started using chess books as training materials.

  2. The AI's illegal moves in chess was easy to fix, you could just hook it up a rule verification tool that constraints its options to legal moves only (this is possible because chess is a closed system with computable rules). So they didn't really improve, they're playing at the same level as before (decent, but nothing more)

  3. you should actually ask why the model is performing each move, if they're better the cool thing is that they can teach us more than stockfish, when you don't understand ask him. Try to make another video asking the logic behind hard moves. Also if they cannot explain the move, then they're using stockfish

  4. you should do an eventual like candidates esque tournament with the top LLMs, and have an entire video series that goes through each stage in the tournament etc. where the first time around the top 2 LLMs fight against each other for the word title, and then we do the same thing next year. you can change it up however you like but i think something along those lines would be really fun to watch.

    (i do remember you making a similar video about a tournament with the LLMs which was fun. but i think it could be quite interesting if the tournament could be a bit more serious/formal this time around and became an annual video series.)

    [edit: made this comment with 40 seconds remaining in the video but i still stand behind what i said.]

  5. That's amazing. I knew that if you make them repeat the moves and "see" the board with ASCII characters, even weaker LLMs are able to play chess (for instance a simple Gemini Flash free won against me). Now these super LLMs have very huge context so they'll remember everything. Interesting the progresses they made so far!

Leave a Reply

Your email address will not be published. Required fields are marked *

You might like

© 2026 Cantinho do Vídeo - WordPress Video Theme by WPEnjoy