WillieCrypto.Eth

@Teknium @NousResearch @Teknium . This sounds very similar to paperclip???

@NousResearch Time to make myself a bunch of different specialist agent profiles with their own skills and memory!

Hermes Agent now has multi-agent via the Kanban, new in v0.12.0. Agents claim tasks from a board, work in parallel, and hand off when blocked. You watch progress and unblock from one easy view instead of juggling terminals. We asked it to plan and make this video about itself:

@LukeMikic21 That video spoke absolutely nothing about trillions. You are just making shit up

Fox News just told MILLIONS of viewers that TRILLIONS are waiting to flood into Bitcoin the moment Clarity passes this month!!! Is the biggest capital flood in Bitcoin history just WEEKS AWAY?!!! ⚡

@rileybrown @Rasmic Huhh ! No Hermes Agent ????

2026 is the year of Agents OpenClaw, Claude Code, Codex and Cursor... In this video, I broke it all down with @Rasmic. Consider this a 2026, year in review for AI agents. 00:00 Intro 01:35 Q1 Belonged to Anthropic 03:02 Opus 4.5 Inflection 08:42 Codex vs Claude UX War 12:53 Cursor was first? 14:27 SpaceX Acquisition Deal with Cursor 21:45 OpenClaw and the Agentic Personal Computer 28:57 Reactive vs Proactive Work 30:30 Keep Agents Narrow 33:12 Memory Layer Matters 36:23 Computer Use will get FAST 39:28 Who Wins the Super App? (Codex so far) 41:06 The Problem With Google... 45:17 Prompting and Skills creation 51:30 Codex Skill Example 56:56 Integrations Beat Prompts 59:39 All the Muxes (CMUX, TMUX) 01:02:04 Bold Predictions 01:06:38 Agent Commerce

@AlexFinn @AlexFinn I bet this prompt would be even more valuable using Hermes with ChatGPT 5.5 as its brain. This would be a 10x.

5.5 BUSINESS PROMPT: You are my brutally practical cofounder. I’ll give you my background + interests. Your job: generate app + business ideas that are actually shippable and sellable, not generic “AI habit tracker” trash. My profile Career/skills: I'm a content creator who makes tweets and videos about vibe coding Interests/obsessions: AI, technology, entrepreneurship, investing, business People I can reach / distribution: 200,000 on youtube and 400,000 on X What I refuse to build: super massive, expensive, large scope projects Time/complexity limit: 2 months Platforms: iOS app or web app Output rules Give 8 ideas. Each must have: Name (2–4 words) One-sentence pitch Target user Pain it solves (specific) MVP in 5 bullets (smallest real thing) Why this wins (1 clear differentiator) Monetization (price + model) Fast distribution angle (how you’d get first 100 users) Build time estimate (Weekend / 1 week / 2–4 weeks) Then pick the best 1 and give: a 30-second founder pitch a 7-day execution plan (Day 1–7, concrete) the first 3 screens (or pages) it needs Hard constraints No saturated ideas (todo, generic journaling, generic habit tracking, generic “AI chatbot wrapper”). At least 3 ideas must be “weird but plausible” (novel combo of my interests). Keep it tight. No essays.

ChatGPT 5.5 is an EXCELLENT model Way bigger than just a .1 upgrade For the past day it's been creating some amazing business ideas for me. It's also an EXCELLENT creative writer You need to be jumping on these models the moment they drop Here's how you should be using it: 1. Every knowledge task you do feed it through 5.5. Ask how it could help or do the task better. You'll find AI use cases you never thought of before 2. Have it create artifacts. 5.5 is AMAZING with tool calling. Have it research AI related stocks and build a spreadsheet of bull cases, bear cases, performance, and moats 3. Create projects inside of ChatGPT for any app you're building. Drop in a current state doc and a vision state doc. Ask it how you can bridge the 2. You'll get some excellent actionable steps If you do these 3 right now you're ahead of 99% of people. In fact, I'll make it easy for you. I'll give you a prompt that helps you generate new business ideas in the next post down below. Just fill in details about yourself and you're all set. It really demonstrates the creative power of 5.5 Props to OpenAI for this one. It's unreal it's only been a month since their last update.

@gdb Can you migrate your Lovable project to codex. Please say YES

Codex is for everyone, for any task done with a computer

@aakashgupta Can you migrate your Lovable project to codex?

Codex was a coding agent. Today it's a general work surface. Look at the role picker: Engineering, Product, Finance, Marketing, Sales, Operations, Design, Data science, Student. The coding tool just became the work tool. This is OpenAI building a harness layer on top of their own model. Anthropic ran the same play first with Claude Code. Wrap the model in file access, multi-step planning, tool calling, app connections. The work shifts from typing into a chat box to delegating to an agent. 900M weekly active users on ChatGPT, and 75% of conversations are non-work. Codex is targeted at the other 25%, where most sessions stall around step two or three. The harness is becoming the actual product, and the role picker tells you OpenAI knows it.

@Base44 What's the benefit of Migrating and existing project to your platform? Aren't you and lovable the exact same tool ?

Introducing: Base44’s new platform migration feature. If your needs have outgrown your current software, you can now bring your projects from other platforms into Base44 in a single click. This includes your Salesforce pipeline, Shopify catalog or WordPress site. Also whatever you’ve built on Lovable, Bolt, or Replit. To celebrate the launch, anyone who completes migration by May 5th, 12am ET gets 25 free credits added to their account!

@DataChaz @stripe How do we monetize this as a business?

DO YOU EVEN REALIZE WHAT'S HAPPENING? @Stripe just gave AI agents a wallet. Soon, bots will be spending billions on behalf of humans and companies. The "Service as a Software" (SaaS v2) market is at $0 today. We must build platforms designed for agents to buy from, not humans. This marketplace is completely empty. WAKE UP. WIN. x.com/stripe/status/…

@_MaxBlade @_MaxBlade is codex and gpt -5.5 used inside Hermes or run side by side as a system??

How to start winning : Install Hermes on your MacBook. Get a $100 a month codex subscription and have it run on gpt 5.5 Don’t waste time on anything else. It has absolute frontier intelligence and they have made soo much improvements to the personality. It feels like working with a friend. ( kind of scary tbh ) The amount of tokens you get subsidized with running gpt 5.5 through the codex cli is unbelievable. Give hermes GitHub access, ssh keys to your servers, and cloudflare tokens. It will take your local project and put them live on the web with domain, dns, ssl, nginx, pm2, everything setup in just ONE prompt. It can monitor your backend / database and make sure everything is running perfectly. Give it a support email, when customers reach out instruct it to look into there account on the server and makes any non destructive fixes. Hermes will automatically turn everything it does into skills, getting better and learning from mistakes constantly. You can literally have a 250k a year highly technical employee that WORKS 24/7 for $100 dollars right now. I need you to wake up.

@_MaxBlade I dont see the benefit of this. What. I MISSING ???

You realize what this means!? Stripe just gave you a new way to create generational wealth. They invented an entirely new marketplace. Agents will be spending millions, and eventually billions of dollars for individuals and corporations. The marketpalce is empty right now. IT IS YOURS FOR THE TAKING. Build a service as a software ( YES SAAS V2 ), make it so that agents can use and spend on your platform. WIN WIN WIN. WAAAAAAKE UPPPPP.

@LoicBerthelot Hermes

As a founder, which team are you on? 1. Hermes 2. OpenClaw 3. Claude Dispatch

@gregisenberg Boring businesses where you know the whole entire workflow and pain points 👉

What are the best businesses to be in a post-AGI world?

@Alex_Kozora What I'm puzzled by is how the guys on the panel are actually laughing at this. Like, that's freaking crazy.

Really sucks for McCoy. Great tape. But heavy medical concerns, and Steelers probably extra cautious after Trice's repeated injuries that followed him to the NFL.

@Blitz_Burgh Skyler Bell or Bryce Lance. I'm not comfortable with Roman Wilson as number four receiver right now. That needs competition.

Who do you want the Steelers to draft on Day 3? #Steelers #NFL

@Zephyr_hg "IDEAS"

50 AI businesses you could start this weekend. Pick one. Every idea comes with a revenue path, MVP scope, and exact tech stack so you're not guessing what to build or how it makes money. Organized into 5 categories: vertical agents, content tools, data infrastructure, edge AI, and services. Medical billing agents. Construction safety cameras. Prompt injection firewalls. Drone inspectors for solar farms. Each one scoped lean enough to validate in 48 hours with a simple ad or DM campaign. No more staring at tech trends trying to figure out where the money actually lives. Pick the lane that fits your skills and ship the tiniest possible version before your competition finds these ideas. Comment "IDEAS" and I'll DM it to you (must be following)

@Steelersdepot Solid B-

Grade the selection of WR Germie Bernard. What are yinz thoughts on him? #Steelers #NFL

@Steelersdepot WR Chris Bell CB Jermod McCoy CB Denzell Boston DT Kayden Mcdonald WR Ted Hurst

Give me yinz list of 5 players you would like to see the Steelers attack on Friday night. #Steelers #NFL

@Jason I'm in

We started an AI founder twitter group... reply with "I'm in" if you're a founder and want to be added

@Kimi_Moonshot Will it work on a mac mini M4 chip with 16gb ????

Kimi K2.6 demonstrates strong long-horizon coding in complex engineering tasks: Kimi K2.6 successfully downloaded and deployed the Qwen3.5-0.8B model locally on a Mac. By implementing and optimizing model inference in Zig—a highly niche programming language—it demonstrated exceptional out-of-distribution generalization. Across 4,000+ tool calls, over 12 hours of continuous execution, and 14 iterations, Kimi K2.6 dramatically improved throughput from ~15 to ~193 tokens/sec, ultimately achieving speeds ~20% faster than LM Studio.

@JulianGoldieSEO The cost is ridiculous. No thanks

𝗢𝗽𝘂𝘀 𝟰.𝟳 + 𝗛𝗲𝗿𝗺𝗲𝘀 𝗝𝘂𝘀𝘁 𝗺𝗮𝗱𝗲 𝘁𝗵𝗲 𝘄𝗶𝗹𝗱𝗲𝘀𝘁 𝗔𝗜 𝗰𝗼𝗺𝗯𝗼 𝗼𝗳 𝟮𝟬𝟮𝟲. Opus 4.7 checks its own work before it ships. It jumped 13% on coding tasks over 4.6. Hermes is a free open-source agent that remembers. It writes a skill after every task and reuses it. Text it from Telegram, WhatsApp, or Slack. Setup takes 10 minutes. One command. Your agent gets smarter every single week. Save this. Your new team member never sleeps.