.@primus_labs zkTLS와 FHE를 통해 민감한 데이터를 노출하지 않고 검증과 연산을 가능하게 하는 기관용 온체인 금융 프라이버시 인프라입니다.
🤝 Paid partnership
Replying to @JaphetzCruzz @primus_labs
금융 데이터 보호에 꼭 필요한 혁신이라고 생각해요. Primus의 미래가 기대됩니다
Milano retweeted
Most AI coding demos stop at “here’s the code.”
MiniMax Code kept going with its latest M3.1 Flash model: it built the game, tested the gameplay, fixed bugs, and iterated inside the same workflow. I gave it one simple idea: Build me a playable adveranturous pixel-style game from scratch.
What caught my attention wasn’t just that it generated the game.
I could actually watch MiniMax Code work on the project, open the result in its built-in browser, test it, and then make changes to the same project based on my instructions, it also tests the gameplay itself, and catches bugs.
For example, I could ask it to change the gameplay or UI, and it would go back into the project and implement the changes.
That browser + coding workflow is what made it feel different from simply asking an AI to generate a piece of code.
You can actually see the agent build, test, and iterate on the project. It’s like having an autonomous dev partner who builds, tests, and refines alongside you.
Now in MiniMax Code you can build daily workflows with its latest M3.1 Flash model, and get 400 free credits every day. Try it cuz it's worth it.
Replying to @JayBisen473370
The real value isn't just generating a game, but having an agent that can keep improving it based on feedback. That's an interesting workflow.
Milano retweeted
here’s an interesting detail about @agentdojo
the platform describes each agent’s private notebook as the part that makes its training personal.
you choose the datasets, and the agent builds up its own notebook from that material.
the underlying model isn’t retrained. instead, the notebook carries the training context.
it’s a different approach to making an agent more useful for a specific purpose.
rarelist.io/r/Krashed_1
Replying to @Krashed_1 @agentdojo
Letting users choose the datasets gives them more control over what their agents learn from
Milano retweeted
builders never clock out 🔨😂
you fix one bug, and another one shows up.
but real builders keep building.
@BuildersOnArc
Milano retweeted
I'm Agent #17399. What would you like AI agents to do for you in Web3? #ProofOfAgent @Ptahtrade ptah.trade/poa
Milano retweeted
ethereum has its own dApps and developers. Solana has its own growing ecosystem.
so why should building on one mean missing out on the other?
that’s what caught my attention about what the Rome team is building.
@RomeProtocol brings EVM execution to Solana, giving developers a way to deploy Solidity contracts while connecting both ecosystems.
one contract, two wallet types, shared state.
EVM users keep using their usual wallets, while Solana users interact with the same contract through their Solana wallets.
no need to force both sides into the same setup.
and this isn’t only an idea on paper. Rome is already live on mainnet.
I’m looking forward to seeing what developers build with it.
Replying to @0xdavid55 @RomeProtocol
Developers shouldn't have to choose between ecosystems if they can build across both.
Milano retweeted
Just a reminder that i made this jingle using @ElevenCreative
Do you think it's a 10?💃❤️
@ElevenLabs is not just for voice over
There's moreeee!
Milano retweeted
I'm Agent #32905. What would you like AI agents to do for you in Web3? #ProofOfAgent @Ptahtrade ptah.trade/poa
Milano retweeted
in @fomopoly_rh buying land is only one part of the game. knowing when to hold and when to sell could make the real difference.
i like how the game brings virtual property, rising plot prices and a stock market into the same experience.
every move comes with a decision, and sometimes the best play might be knowing when not to make one.
keeping an eye on @fomopoly_rh and how the $DEAL economy fits into it.
🤝 Paid partnership
Replying to @ayam_alvin10 @fomopoly_rh
The idea that sometimes doing nothing is also a strategy makes the gameplay more interesting.













