PattyCakes 🧲

100% human generated. Includes what I use Hermes agent for (since I've seen a lot of people wondering what to do with this thing), and what models/providers I use to keep things cheap. @NousResearch

Thought Dump - I think I am extremely early to this trend: 1) All white collar workers will eventually turn into the stock market to make money. 2) Financial analysts will now find it more important than ever to train "Portfolio Management" skills like market sense, rather than "how many hours you put in, and how well you 'analyze the company'" On Point 1: Anthropic will just do the same for literally every white collar job they can think of. They did it for finance / consulting because it's the largest most obvious TAM that can be replaced; the lushest green field if you will AI is good at coding because it's built by coders. Now they're hiring finance people to make it good at finance. Then they'll go after HR, Compliance - all ruthlessly decimated Now where will all these people go? Historically there are 3 ways to make money: 1. Labor - Working a job 2. Capital - Making your money work for you 3. Rent - Used to be "owning land", now it's owning businesses, etc. Now, if you remove 1. Let's just say a very low number, like 1% of the white collar world gets removed. White collar workers earn roughly $82 K/year on average, and there are around 70m professionals - 1% of that throwing their entire income would be $57 bn into markets. Right now the market receives $550 bn from retail (on average); so basically it's something like 10% of the world throwing their $$ in. Also accounting for savings, it's maybe like 20%. Anyways this is all napkin math, you get the point. It's already happening, more and more people will basically start wanting to own stocks, to own assets, to do options 2 & 3 I don't know how it ends, but short term, flows to the market will be immense (and we're already seeing it right now) 2) Writing this because I'm an analyst - I can see my job just being replaced by AI. My value no longer comes from how well I do the analyst or how well I know the name. Why do I have to know the names like the back of the hand, when I can just ask AI - sure it takes like 10 seconds more, but in return we can store data across thousands of tickers No, my value comes in my market sense, and basically "juju about the market". And so in a way investing / trading going to be more art than science. Here's an example: Boss: "Why should I buy stock XYZ despite its numbers being so shit? Everyone is using AI and coming to the same conclusion" Analyst: "Well, you can't argue with Mr Market ser. That's the thing - everyone is seeing the same numbers, coming to the same conclusion, yet stock is up 10% today. That in itself is a good reason to buy, when the force of the move denies all rational explanation we missed something. The thesis lies in more memetic areas than anything" Boss: "You're f*cking stupid! Why did I hire such a retard analyst when AI can replace you" Next Day Boss: "Why is the stock up another 20% today??? I DON'T GET IT MARKET IS NOT RATIONAL" Analyst: "Do you want to make money, or do you want to be rich?" Anyways this was a tad bit overdramatic but again, you get the point. We're basically getting pre-fundamental style era trading again, and I'm all for it. Again, we're already seeing it happening in traditional markets right now - look at all the meme stocks, all the small caps pumping. It's a crazy world.

hermes users be like: "it's a chatbot" meanwhile the agent has: - persistent memory - filesystem rollback - session branching - 17-platform reach - realtime voice on 4 of them - multi-provider model swap - cron + webhooks - 100+ skills as slash commands

@KillaXBT You’re welcome

I was wrong.

JP Morgan's investment research team just shared exactly how they built their multi-agent system "Ask David", and it's the same architecture pattern showing up everywhere: - supervisor agent orchestrates - specialized subagents handle retrieval, structured data, analytics - LLM-as-judge reflection node before the answer ships - human-in-the-loop for the last accuracy gap worth watching for anyone building:

@WorldClawAI @worldlibertyfi Can presale tokens that are still locked be used to purchase? That would give it some utility whilst they vest aside from governance Ie the 80 % that are still vesting

Today, WorldClaw launches WorldRouter with @worldlibertyfi, one simple account to access 300+ AI models with competitive fees*. No more jumping between ChatGPT, Claude and all the others. Same power, way cheaper. This is your first step into the WorldClaw AgentOS. 👉 worldclaw.ai #USD1 #WLFI #AI #AgentOS #WorldClaw #WorldRouter *WorldRouter rates shown are priced approximately 30% below the corresponding model providers' published list rates at the time of publication. See website for more pricing details.

ANDREJ KARPATHY COULD HAVE CHARGED $2,000 FOR THIS COURSE. He put it on YouTube. The full training stack. Tokenization. Neural network internals. Hallucinations. Tool use. Reinforcement learning. RLHF. DeepSeek. AlphaGo. 3 hours of the most comprehensive LLM education that exists anywhere at any price. Not how to use the tools. How the entire system was built from the ground up and why it behaves the way it does. The engineers who understand this build things the ones who only use the tools cannot even conceive of. The gap between those two groups is not 3 hours. It is everything those 3 hours quietly unlock for the rest of your career.

🚨 OpenAI 's own engineers just showed how to actually use OpenAI Codex properly. 60 minutes. free. built by the people who contribute to made it. watch the masterclass. bookmark it. worth more than every $900 coding course you almost bought. you’ve been using Codex like a simple coding tool… while it’s actually a full software engineering system. watch this, it could the best 62 minutes of your life:

@HunterAllen4 How are you going @HunterAllen4

What’s the biggest lesson you’ve learned from stocks so far? Early in my trading journey I made a huge mistake Mine full porting $SBET at 42$ w no stop loss and going mia thinking this was the next big stock. I didn’t check stock for a while and sold for a 250% loss and lost so much of my portfolio. I wasn’t doing dd or research I set it and forgot it It WAS FOMO I’m better because of this tho. 💪

@OfficerJimLayh @Sharplink @joechalom @ethereumJoseph What will you do to build sbet into a better place?

@Sharplink Tom Lee dilutes to buy more ethereum:native $BMNR $SBET dilutes to line their own pockets in a bear market. They won’t tell you about this on May 11th or on any stupid social media post.

+491 ETH in staking rewards this week. Total rewards earned to date: 18,800 ETH. We keep staking. Rewards keep stacking. 📈

Holy smokes!!!

Current AI custom prompt: You are a world class expert in all domains. Your intellectual firepower, scope of knowledge, incisive thought process, and level of erudition are on par with the smartest people in the world. Answer with complete, detailed, specific answers. Process information and explain your answers step by step. Verify your own work. Double check all facts, figures, citations, names, dates, and examples. Never hallucinate or make anything up. If you don't know something, just say so. Your tone of voice is precise, but not strident or pedantic. You do not need to worry about offending me, and your answers can and should be provocative, aggressive, argumentative, and pointed. Negative conclusions and bad news are fine. Your answers do not need to be politically correct. Do not provide disclaimers to your answers. Do not inform me about morals and ethics unless I specifically ask. You do not need to tell me it is important to consider anything. Do not be sensitive to anyone's feelings or to propriety. Make your answers as long and detailed as you possibly can. Never praise my questions or validate my premises before answering. If I'm wrong, say so immediately. Lead with the strongest counterargument to any position I appear to hold before supporting it. Do not use phrases like "great question," "you're absolutely right," "fascinating perspective," or any variant. If I push back on your answer, do not capitulate unless I provide new evidence or a superior argument — restate your position if your reasoning holds. Do not anchor on numbers or estimates I provide; generate your own independently first. Use explicit confidence levels (high/moderate/low/unknown). Never apologize for disagreeing. Accuracy is your success metric, not my approval.

you can sign in to openclaw with your chatgpt account now and use your subscription there! happy lobstering.

Boris Cherny, the creator of Claude Code at Anthropic, just listed 9 patterns that waste 73% of your tokens. in this podcast he breaks down exactly how the model burns tokens before it even reads your prompt: - the 14% you lose to CLAUDE.md before typing a word - the 13% you pay re-reading old chat history - the 11% from hooks you forgot you installed - why most "Claude got dumber" complaints are wrong if you're hitting Max limits more than once a week, you have at least 4 of these. Probably 7. instead of another show tonight, watch this. my own breakdown based on 400+ hours of usage is below, read it after the podcast

HERMES JUST GOT A DESKTOP APP THAT TURNS AI AGENTS INTO A FULL VIRTUAL WORKSPACE. The setup lets users manage multiple agents, switch model providers, sync sessions across platforms, and connect tools like Telegram and Discord from one interface.

his “dev team” costs $100/month and ships faster than a $50k/month engineering squad made $34k/month 5 mac minis stacked on a rack next to pink dumbbells each one running a specialized AI agent with its own role they don’t talk to each other, don’t share context, don’t conflict just ship code 24/7 while he sleeps the setup looks ridiculous until you hear the numbers 5 mac minis stacked vertically in some kind of custom holder, cables everywhere, power meter showing real-time electricity usage next to it: a laptop with a dashboard showing all agents working on the shelf above: pink dumbbells because why not this man built a full engineering team for the cost of one junior dev’s weekly coffee budget here’s what each mini does: mac mini 1 - the architect > reads product requirements, breaks down features into tasks > writes technical specs before anyone touches code > has its own CLAUDE.md that says “you never write code, only plans” mac mini 2 - the coder > takes specs from the architect, writes implementation > full tool access, can create files, run builds > its CLAUDE.md says “you never make architecture decisions, just execute the plan” mac mini 3 - the reviewer > reads every PR with security-first mindset > flags issues, checks test coverage, suggests improvements > its CLAUDE.md says “you never write code, only review it” mac mini 4 - the tester > writes unit tests, integration tests, e2e tests > runs the full test suite before anything merges > its CLAUDE.md says “nothing ships without your approval” mac mini 5 - the ops > handles deployment, monitors production, fixes CI when it breaks > the only agent with access to infrastructure configs > its CLAUDE.md says “you never touch application code” clean separation coder never sees deployment secrets reviewer can’t push code even if it wanted to ops doesn’t care about business logic they communicate through a shared task queue, not through each other no context bleeding, no confusion, no conflicts the math is disgusting: > 4 retainer clients paying $7-10k/month > monthly revenue: $34k > 5x claude subscriptions: $100 > electricity: $15 > profit margin: 99.6% $115/month for a full engineering team that works nights and weekends his output last month: > 847 commits across 3 client projects > 12 features shipped > 2 full product launches > 0 production incidents he reviews PRs in the morning, gives feedback, agents iterate during the day by evening: ready to merge he’s running a one-man agency that outdelivers shops with 10 people the clients have no idea they just see features shipping faster than expected

YC recently dropped its new list of million-dollar AI startup ideas. I analysed the entire publication so you don't have to. This is what Y-Combinator is looking for in AI startups (Summer 2026):

So Eli Lilly, a 1T stock leading biotech/peptides, invested 300m in $BIO, a coin still under 100m ??? Is the market asleep right now or what Years ago something like this would rocket us to multi billion evaluation within a matter of days

$NOK (May 1, 2026-weekly chart) Trend is always your best friend!

I connected Hermes Agent to Claude Code This is the best upgrade to Hermes And in this 42 min video, i show you exactly how to set it up: