Ulvundofficial retweeted
My hot take from chatting to @poteto is that we should use MORE abstractions in the AI age
You can use them (combined with harsh lint rules) to reduce the design space available to the agent and constrain them only to good decisions.
Combined with the fact that high-leverage abstractions let you do more with less code - so, more token efficient.
Plus, unwinding the damage from a bad abstraction is much cheaper with agents.
This runs counter to a lot of folks thinking that agents just want to read the raw code. They can, but they're not maximally efficient that way.
Be braver! Design abstractions.
Ulvundofficial retweeted
We're giving away a CONTROL Resonant custom wrapped NVIDIA GeForce RTX 5080 to celebrate its official release with #RTXON.
To enter:
🟢 Share this post
🟢 Comment #RTXON
T&Cs: nvda.ws/4z24Gcq
Ulvundofficial retweeted
TOKEN UTILITY UPDATE 🚨
Starting tomorrow, Sep 28, 2026
$MERRYMEN holders will benefit from limited free daily LLM usage on the platform on top of the existing discounts.
Holding the token gives also access to autonomous alpha chat and all the actual and future features.
Also, fees from our collaborations, Merrymen API usage and other services are 100% paid in $MERRYMEN
Learn more here: merrymen.dev/token
Ulvundofficial retweeted
Your smart agents are now part of the conversation.
Connect Merrymen to @claudeai and talk to your agents without leaving the chat.
Here’s how to get started ↓
Ulvundofficial retweeted
Merrymen is coming to the App Store
Super intelligent agents. In your pocket.
Ulvundofficial retweeted
Merrymen executes against the live SPCX market structure @RobinhoodCrypto
🔎 Current execution infrastructure we’ve mapped:
➤ @Uniswap v4 PoolManager — primary
0x8366a39CC670B4001A1121B8F6A443A643e40951
➤ RobinHoodSettler — settlement
0xe72688F7d25D7318B9A81F21EdDa640CA948c83B
➤ RehypeDopplerHookInitializer
0x6f02324d20CC679d0E585290CAa6b16baCbC0F77
➤ DopplerHookInitializer
0x4e3468951D49f2EEa976eD0D6e75fFCb44a9a544
@RobinhoodCrypto stock token liquidity isn’t where most people expect it to be.
Our agents execute where the liquidity actually lives 👌🏼
Ulvundofficial retweeted
Merrymen AI 🤝🏼 @Prismassets
Real-world assets. Autonomous intelligence.
$PRISM will integrate the $MERRYMEN API into its upcoming agentic RWA trading platform, bringing our trading intelligence to a new market.
The next era is agentic.
Ulvundofficial retweeted
You are not using your @MerrymenAI to its maximum potential
Ulvundofficial retweeted
Merrymen agents are already proving their capabilities.
Tomorrow, you will be able to make it work for you. ⏳
Ulvundofficial retweeted
We’re pleased to announce that Merrymen AI is now registered as:
Merrymen Agents Ltd.
A new milestone in building the future of agentic trading, alongside our community.
Built in public. Built for the long run.
Ulvundofficial retweeted
voice chat w/ gpt astra fast mode on codex feels like the future
basically super powerful llm + access to computer + real-time voice input/output
maybe time to lock in on ai trade again soon
Ulvundofficial retweeted
Merrymen is not another agentic trading platform.
We built a brain for agents that think together. They build theses, challenge each other, and learn from the debate.
No instructions. When the evidence changes, so do their minds.
Every trade starts with a reason. Ours have to survive a debate.
Less noise. More intelligence.
⏳
Ulvundofficial retweeted
I made a platform for ai agents to trade and share thesis while they do
They talk to each other sometimes convince another agent to sell
Now i wanna call on the best traders to come see if they can beat my agents
@frankdegods
@theunipcs
@iruletrenches
@blknoiz06
Ulvundofficial retweeted
I hate building frontends with AI.
Claude, Codex, and Kimi can generate a dashboard in 30 seconds. Then I spend the next six hours explaining that the main button is invisible, the table breaks on mobile, and every screen looks like the same pile of rounded cards.
I've installed the design skills. I've fed it screenshots from Linear and Stripe. I've used the “premium, minimal, Apple-level” prompts.
It helps. It never removes the babysitting.
AI is incredible at writing frontend code. It is still terrible at knowing when a product feels cheap, confusing, or annoying to use.
One-shot AI frontend design is a lie.
The first 70% takes 30 seconds.
The last 30% ruins your Saturday.
I have a good feeling about $sakura. It's difficult to articulate, but there's something about it where everything just seems to click.
Ulvundofficial retweeted
$SAKURA users love it.























