Gemini Argon 4 destroyed me in chess. I’m done.



Get My New Intermediate Book Out NOW:

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

47 Comments

  1. I think the idea of going easy and giving them a chance undermines the idea of this, it might be a personification that's born from that additional text that comes with the move. I'd be much more interested in hearing what the LLM says when you explain why a move is wrong or establish that you have deep knowledge because I find LLMs tend to have this 'meet you where you are' element.

  2. I pretty much watch whatever you make. Recaps are the best, slowruns are second. The super high level bots playing each other is cool too. That would probably lose it's appeal if you overdid it. Idk, I like whatever you do. Just keep doing your thing and make stuff you enjoy making. Take brother, you do a good job.

  3. 26:21 this is not the model's fault btw, they give it minimal context windows so you don't overload a chat and bypass security restrictions so that overtime the llm compresses the size of the context in the chat so they lose track of the locations of the pieces on the board. I think you should ask them to keep track of the moves with notations in each response they give you so that they can keep track or check it when they lose track

  4. your youtube title in this video is misleading! I am going to search at least one game in youtube where you get destroyed, so I can abide by your youtube title. Regards…

  5. Hi Levy I’m from India. I just bought your second book. It’s really great. Don’t act as if your career has ended due to AI. It’s just another branch of software. Please continue writing books like this. We are all behind you.

  6. I think it would be really interesting to test both LLMs playing chess directly, but also LLM-written chess bots, and LLMs assisted by bots they wrote themselves: so you could tell astra or opus "you will play chess tomorrow, you have one day to write a chess bot to assist you in the match", etc.

    You'd have to find a way to limit the number of tokens the model can spend writing the chess bot, otherwise all the bots will probably just converge on a vibe-clone of stockfish, but if you give them some tight limits in time and tokens, but given how good these LLMs are supposed to be at coding, an approach like that could give a much more accurate view of their real strength.

    Also you should get jev to play blitz

  7. I enjoy these videos. It's nice to know that the super brain still can't play chess. Or rather it can, but it still can't grasp, like, the rules.

    However good it is in the moment, the fact that it doesn't understand rules that you can teach to a ten year old in a few minutes is somewhat fascinating.

  8. what a fun series, been watching since the last few days and really enjoying it! thanks for everything you do, you genuinely are so entertaining but ALSO knowledgable <3

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