Been quiet for awhile now.
Just learning and building on recent techs. 🤖
Now I’m back to share what I’ve been exploring:
• LangChain
• RAG (Retrieval-Augmented Generation)
• Vector databases & LLM pipelines
• Agent frameworks
• And soon… exploring how all this might connect with blockchain — and maybe build something cool.
The biggest advancement in AI coding this year has been /goal
And it isn't even close
It allows your AI agent to quite literally work for days without stopping. You give a mission. It works until the mission is complete
Here's the thing though: /goal is useless if you don't use it properly
You NEED a good prompt for it
I found basically any prompt I hand write after /goal is never good enough. It produces results that might as well have been a normal prompt
Meta prompting is the answer
Go to any AI that has context around the project you're working on
Say "I'm working with Codex and I want to use their new /goal feature. Please research their /goal feature. Then, take a look at our project and give me 3 options for how we could use /goal to be maximally productive. Then give me a highly detailed /goal prompt for each"
Take one of the prompts then go into the Codex CLI and type /goal then give the new prompt
I 100% guarantee the AI does better work than you've ever seen before
Every AI tool you need to escape the permanent underclass:
• Codex app (5.5 medium on fast mode)
• Hermes Agent (powered by local model)
• OpenClaw (ChatGPT 5.5 oauth)
• Gemma 4 running on a Mac Mini
• ChatGPT 5.5 Pro for planning
• Claude Design for front end design
• Claude Code for front end development
• ChatGPT Image gen 2 for more than you can imagine
• Spotify playing lofi bangers
• 2nd monitor that has these agents up 24/7
Do work on 1st monitor. Constantly prompt 2nd monitor
CLAUDE CODE CAN NOW COPY ANY UI ON THE INTERNET.
It scans real websites and rebuilds their design system instantly, turning any page into your own starting point.
Claude for Word is now in beta.
Draft, edit, and revise documents directly from the sidebar. Claude preserves your formatting, and edits appear as tracked changes.
Available on Team and Enterprise plans.
My mind is so blown
I have my own personal AI research lab running 24/7/365
I'm just one dude with an entire team of AI agents training models and doing R&D
I think this is the biggest opportunity right now: taking Karpathy's Autoresearch framework and applying it to everything
I have a team of AI agents running experiments all day and night on system prompts, local models, and LoRAs.
I also have them doing R&D on my new project. They spend all day discussing my app, coming up with new ideas, then debating eachother
An entire organization of autonomous agents continuously improving my business 24/7/365
I feel like I have unlimited power
Right now they are all running on ChatGPT 5.4, but today I will move them to local models running on my 3 Mac Studios and DGX Spark so this will all become free
Free, local super intelligence working for me at all times.
10 year old me would think this is a scifi
Do this immediately:
1. Ask your agent about Karpathy's Autoresearch. Deeply understand it
2. Ask your agent how you could apply that framework to other projects you're working on
3. Download a local model. Doesn't matter what computer you have. There is a model you can run on it.
4. Just get used to how it works. Learn from it.
5. Push yourself to get uncomfortable every day and try new things.
There has never been a better/more profitable time to be a tinkerer
HyperCore will support outcome trading (HIP-4). Outcomes are fully collateralized contracts that settle within a fixed range. They are a general-purpose primitive that are useful for applications such as prediction markets and bounded options-like instruments. There has been extensive user demand in both of these areas, and builders will likely think of novel applications as well.
Outcomes bring non-linearity, dated contracts, and an alternative form of derivative trading that does not involve leverage or liquidations. The outcome primitive expands the expressivity of HyperCore, while composing with other primitives such as portfolio margin and the HyperEVM.
Outcomes are a work in progress and currently only being tested on testnet. Canonical markets based on objective settlement sources will be deployed once technical development is complete. Canonical markets will be denominated in USDH. Pending user feedback, the infrastructure will be extended to permissionless deployment.
@ericw_ai This is actually very beginner-friendly! Understanding the full pipeline of building an agent before diving straight in, for easier debugging and fine tuning.
Great write up, thanks for the share!
Just unlocked my Gas ID via ETHGas 🪪
I'm a Hero Jack with 4.76 ETH spent on gas since Beacon Chain - now fueling my climb to the Gasless Future and earned 3000 Beans already.
Reveal yours at https://t.co/OBcFIGnoay
coming soon to @BullpenFi
first pro terminal for prediction markets
powered by @Polymarket
join the waitlist for early access: https://t.co/GvyWmPZH9d
all @Polymarket & @PolymarketTrade@X badge affiliates who reply to this post will receive priority beta access