Anshul Dhawan's banner

Anshul Dhawan

@AnshulDhawan001 • 2,845 subscribers

Building Playworlds. Prev product/game dev @zynga, @ea, @getSupernatural, @vrchat.

Shorts

🚨Network Cities Build Update🚨 ✅✅Completed✅✅ 🔄Migrated the entire codebase to TypeScript ⚙️Core functionality now live on the new stack 🚂Added a new transportation: Goods Train 🏗️Implemented initial City Expansion system 🔜🔜Next Up🔜🔜 💰Deeper economy development 🔧Crafting mechanic 🔌Snapser integration 🌐Client/Server communication In the video you see the goods train will run through every city, delivering vital supplies for growth. What began as a Rosebud AI prototype is now on track to launch as a full game. Solana game‑token CA: B45FhPi6d7UR66TGLpQ3EPnWhGfzdGVkCKNp9neR5Cxt Follow Network Cities - $CITIES for game updates.

🚨Network Cities Build Update🚨 ✅✅Completed✅✅ 🔄Migrated the entire codebase to TypeScript ⚙️Core functionality now live on the new stack 🚂Added a new transportation: Goods Train 🏗️Implemented initial City Expansion system 🔜🔜Next Up🔜🔜 💰Deeper economy development 🔧Crafting mechanic 🔌Snapser integration 🌐Client/Server communication In the video you see the goods train will run through every city, delivering vital supplies for growth. What began as a Rosebud AI prototype is now on track to launch as a full game. Solana game‑token CA: B45FhPi6d7UR66TGLpQ3EPnWhGfzdGVkCKNp9neR5Cxt Follow Network Cities - $CITIES for game updates.

19,719 просмотров

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

Presenting Network Cities (@network_cities_), a city builder game where your social network powers your game. The game allows the players to bring in their network without any friction. Bigger your network, the faster you progress in the game. The game follows the basic rules of a city builder game where you collect, build and expand your city. But having an in-game companion in the form of Nikola Tesla provides a new interaction model while playing the game. Because it is powered by LLMs that take the player state as the input, the players always get the right game quests tailored for them. Find the game link in the comments and let me know what you think.

Presenting Network Cities (@network_cities_), a city builder game where your social network powers your game. The game allows the players to bring in their network without any friction. Bigger your network, the faster you progress in the game. The game follows the basic rules of a city builder game where you collect, build and expand your city. But having an in-game companion in the form of Nikola Tesla provides a new interaction model while playing the game. Because it is powered by LLMs that take the player state as the input, the players always get the right game quests tailored for them. Find the game link in the comments and let me know what you think.

139,393 просмотров • 10 месяцев назад

Which LLM reasons best when it doesn't have all the information? Enter LLM Poker Arena to find out. It's a Poker Playing benchmark where top reasoning models play Texas Hold'em poker against each other. Claude Opus 4.5, GPT-5.2, Gemini 2.5 Pro, and Grok 4 all sit at the same table and play full tournaments to see who finishes with the chips. Poker is very different when it comes to reasoning. It has to balance probabilistic reasoning, opponent modeling and make decisions under uncertainty. Poker is an interesting evaluation because it tests reasoning under incomplete information, something most coding benchmarks do not capture. In this tournaments the rules are: - Each LLM starts with $1,000 chips - Small and big blinds start at $25 / $50 - Blinds double every 3 minutes - All models run in their reasoning or thinking modes After the first 5 tournaments: - Claude Opus 4.5 with Thinking has 3 wins - GPT-5.2 has 2 wins - Grok 4 and Gemini 2.5 Pro have 0 wins Early results suggest Claude performs quite well at poker as well. Also five is a very small sample size. Planning to run many more tournaments, publish the full benchmark data and add a prediction market on top of it. Thanks for the suggestion clipz. Much more coming as part of Poker Cities !! This was built on Replit ⠕ using their AI integrations, which made it straightforward to connect Claude, GPT, and Gemini. What model do you think wins after 100 tournaments?

Which LLM reasons best when it doesn't have all the information? Enter LLM Poker Arena to find out. It's a Poker Playing benchmark where top reasoning models play Texas Hold'em poker against each other. Claude Opus 4.5, GPT-5.2, Gemini 2.5 Pro, and Grok 4 all sit at the same table and play full tournaments to see who finishes with the chips. Poker is very different when it comes to reasoning. It has to balance probabilistic reasoning, opponent modeling and make decisions under uncertainty. Poker is an interesting evaluation because it tests reasoning under incomplete information, something most coding benchmarks do not capture. In this tournaments the rules are: - Each LLM starts with $1,000 chips - Small and big blinds start at $25 / $50 - Blinds double every 3 minutes - All models run in their reasoning or thinking modes After the first 5 tournaments: - Claude Opus 4.5 with Thinking has 3 wins - GPT-5.2 has 2 wins - Grok 4 and Gemini 2.5 Pro have 0 wins Early results suggest Claude performs quite well at poker as well. Also five is a very small sample size. Planning to run many more tournaments, publish the full benchmark data and add a prediction market on top of it. Thanks for the suggestion clipz. Much more coming as part of Poker Cities !! This was built on Replit ⠕ using their AI integrations, which made it straightforward to connect Claude, GPT, and Gemini. What model do you think wins after 100 tournaments?

32,192 просмотров • 5 месяцев назад

Больше нет контента для загрузки