Toymaker Jones
@Kybervaul
Building my way out of the Matrix, but I keep getting distracte—🐿️ toymakerjones.base.eth
🕳️ The Monetary Patriot Act No need to destroy Bitcoin. Just wait until it becomes global infrastructure: – Trusted by sovereign wealth funds – Used to settle energy trades – Held by nation-states, pensions, BlackRock – Supporting a world exiting USD Then… trigger the…
AI Agents Evaluation Evaluation is key to developing reliable and scalable agentic systems. Really enjoyed this conversation with @ptkbhv on *everything* related to AI agent evaluation. One of the many deep dives we have done at the @dair_ai academy. Feel free to share with…
Imagine your brain could instantly “adopt” a house rule just because someone told you at the start of a board game (like “today, queens move like knights in chess”), and you’d play by that rule for the whole game—but as soon as the game ends, that rule is forgotten and your…
Haven’t looked into this but this seems to be a prevalent debate! Persistent Agents vs Ephemeral Agents? For those who have read, would love your thoughts! Cc: @omarsar0 @JacksonAtkinsX
What if the most effective AI agent is one that only exists for 5 minutes? A new AI framework called AIME is ditching the idea of permanent agent "roles." It creates hyper-specialized, SINGLE-USE agents for every task, then deletes them. Here’s why this is a game-changer 🧵
This paper is a real banger for autonomous AI agents. It needs to breakthrough. Retweet this one. People need to know about it.
What if the most effective AI agent is one that only exists for 5 minutes? A new AI framework called AIME is ditching the idea of permanent agent "roles." It creates hyper-specialized, SINGLE-USE agents for every task, then deletes them. Here’s why this is a game-changer 🧵
Top AI Papers of The Week (July 14 - 20): - Agentic-R1 - Context Rot - Scaling up RL - A Survey of AIOps - Chain-of-Thought Monitorability - One Token to Fool LLM-as-a-Judge - A Survey of Context Engineering for LLMs Read on for more:
I think I found my new favorite AI Agent guy
A Structural Planning Framework for LLM Agent System in Enterprise Agentic systems for enterprise are a work in progress. Reliability is a real problem. No secret that planning works, but structural planning can further help improve the reliability of AI agents. My notes:
🧵 Futures Contracts 101: How Bitcoin’s Most Powerful Trading Tool Just Went Legit in the U.S. If you care about Bitcoin, TradFi, or markets, this is one of the most important unlocks since the ETF 👇
I enjoyed Madagascar, especially watching with my father. That being said, it doesn’t trump the other series. There is a debate here for kung fu panda to be removed though.
Delete one franchise FOREVER
very interesting to see how different each crypto class is on this app 2013 (bitcoin): early retirement, now they just laugh at everyone else arguing online 2017 (ico era): eth ogs, very philosophically driven and cypherpunk, building toward the “infinite garden” 2021 (nft…
🚨BREAKING: AI can now replace an entire marketing research team worth $300K It analyzes thousands of ads, spots problems early, and tells you what to fix 24/7. Here’s how it works:
🧭 The average person has visited only 2 of these: 20.🏔️ Himalayas 19.🌊 Victoria Falls 18.🇬🇷 Acropolis 17.🛕 Angkor Wat 16.🏺 Petra 15.🖼️ Louvre 14.🪨 Stonehenge 13.🏜️ Grand Canyon 12.💦 Niagara Falls 11.🗻 Mount Fuji 10.⛪ Sagrada Familia 9.✝️ Christ the Redeemer 8.🎭 Sydney…
Builders are awesome
It feels incredible to be working on a product again that isn’t DAUs, but MinuteAUs @baseapp + @xmtp_ First product I’ve ever used in crypto daily, let alone hourly. Hasn’t even really gotten started yet.
America's AI Action Plan is out. The plan is to saturate the digital space with low-risk US artificial intelligence models, fast-track data center construction, and secure high-risk AI projects. 🧵/1
The bills WILL get paid. The stress WILL disappear. Your health WILL improve. Your business WILL flourish. Dear son, God ALWAYS provides.
This is increasingly becoming a more and more viable role given the current landscape. What do y’all think?
So like, we’re really on the edge right now—there’s a new developer role in town: AI x Web3. Prerequisites include: Interests in the following - Ownership of intelligence - @thinkagents - Distributed and decentralized inference contribution @rendernetwork @bittensor_…
Looking to build agents for @baseapp? Here's a full tutorial to help get you started docs.xmtp.org/agents/build-a…
This is a very important tweet.
there's a quiet shift happening in how we design software. we're moving from UX to AX (agentic experience). traditional UX is screen-centric. you tap a button, product reacts, job done. every session starts from zero. designers pre-plan every path with hard-coded flows. users…