Monono

😭

@gmoneyNFT Damn that pixel assemble to punk is FIRE, did you code it up with an agent? 👀

i just made g.money readable by ai agents. not just humans. your agent can subscribe to my newsletter by itself. no browser. no form. just type: POST to g.money/api/newsletter that's the point. if your website isn't agent-ready, you're invisible to the next wave of discovery. i wrote up exactly how i built it. code included. it's the welcome email when you subscribe to the early signal. two ways to get it: 1. go to g.money and sign up 2. tell your ai agent to do it for you

@gmoneyNFT What kinda bugs? On the agent or the code it produces? My stuff worked really good last 2 weeks.

i gave it a shot, but can't do this anymore. hermes sucks ass. all these agents suck ass. they just stop working all the time and then take forever to debug. sticking to claude code and codex in terminal. far and away better than messing with this productivity porn

@chesus @diamante_io Whats cookin? 👀

The Quantum Doom Clock is ticking. This is not a future threat. It is happening now. While most chains are still unprepared, @diamante_io was built for this reality from day one. quantumdoomclock.com

@chesus @diamante_io

@geiztmeta @BitsoOnchain 👀

¡Flappy Derek ya está aquí! 🚀😈 El superhéroe de @BitsoOnchain esquivando dips rojos mortales y volando por pumps verdes épicos. ¿Cuánto aguantas antes de rekt? 💀📈 Juega ahora: flappyderek.netlify.app #DerekOnChain #BitsoOnchain #FlappyDerek #CryptoGame #Onchain

@osf_rekt lol

things to remember before you leave the house: 1. keys 2. phone 3. /remote-control

So many Unnoticed artists out there, This one reminds me of @osf_rekt style

@ultraruidoso @chrisguyot @goodvibesclub @archipixelado This is insane 🔥🔥🔥🔥🔥🔥🔥🔥

✨⚡️🤙 LFV! 🤙⚡️✨ @goodvibesclub

@StephenDGames No way

I made a game world that creates itself as you journey through it…

@JR_OnChain Pokemon gambling sounds like it will be shut down in a day lol

After two weeks of constant 4/5am sleepless nights... I’m about 75% done building an INCREDIBLE crypto based Pokémon gambling game and in my humble opinion, it's going to Break the internet I really want to take it to the next level, but I need just some extra capital to do that... My biggest concern is showing it to the wrong person, only for them to run it through Claude or another AI tool and have someone recreate or steal the idea... Thoughts 🧠

@KCG3D @Austen I activated the his yday, don’t need allow java thing right?

@Austen There’s a new Chrome MCP that came out last Friday that allows for remote debugging and works pretty good!

Pro tip to make agents not suck at doing everything in Chrome: View -> Developer -> Allow JavaScript from Apple Events. Tell your agent you enabled that and it will save a huge amount of tokens for any browser work

@osf_rekt Exciting as fuck 😁

still can't get my head around the rate of improvement literally every day i wake up and there is a major advancement or capability that's been released and the gamma is increasing scary to think where we gonna be by the end of the year

@itsolelehmann Are you guys doing this on your own written skills? I barely made or downloaded skills so far. Maybe the standard GitHub etc. Might need to give in

infinite alpha in this article, but this tops them all IMO (i'm adding this to all my skills): anthropic found a way to make their skills compound on autopilot. every session gets memorized (what it produced, what you corrected, what you preferred) so the skill learns *exactly* how you want things done, and the output gets closer to perfect every single session meaning the more you use claude, the better it adapts to you. over time you barely have to edit anything because it already knows your preferences from every previous session here's how it works: you add a feedback log to any skill. every time you correct claude during a session ("too formal," "shorter subject lines," "i'd never phrase it like that"), it saves your correction to the log next session it reads the log before doing anything else. session 1 through 5 feel normal. you're still correcting things, still adjusting tone, still saying "not like this, more like this" by session 10 the corrections start dropping off. because claude already absorbed the patterns from your previous feedback by session 20 the first drafts are coming back close to done. because the skill now carries 20 sessions worth of your real preferences (and not your imagined preferences from when you first wrote the instructions, your real ones that only surface when you're editing live output) this works across everything: - content: "too formal" / "never use that word" / "always put the cta before the sign-off" → drafts start sounding like you actually wrote them - outreach: "shorter subject lines" / "reference something specific about their business" / "don't open with the company name" → sequences stop reading like templates - client reports: "bar charts, never pie charts" / "recommendation before the data" / "my clients hate jargon" → reports come out ready to send - proposals: "lead with the problem statement" / "pricing on its own page" / "less formal in the intro" → first drafts you'd actually put your name on here's the setup. paste this into cowork: "add a feedback log to my [skill name] skill. create a feedback.log file inside the skill folder. update the skill instructions to: (1) read feedback.log at the start of every session before doing anything. (2) whenever i give a correction or preference during a session, immediately append it to feedback.log. use your judgment on how much detail to include per entry, some preferences are one line, others need a sentence or two of context to be useful. only log general preferences that apply to future sessions, skip anything specific to the current task" cowork handles the rest. takes about 30 seconds it's like onboarding an assistant who takes perfect notes. 30 seconds of setup, and a month in they already know how you think (with unreal precision) run that prompt for every skill you have and give it a few weeks.

@felixrieseberg Just won’t be the same I’m afraid

We're shipping a new feature in Claude Cowork as a research preview that I'm excited about: Dispatch! One persistent conversation with Claude that runs on your computer. Message it from your phone. Come back to finished work. To try it out, download Claude Desktop, then pair your phone.

@ryancarson When are you making a tutorial of your workflow? Maybe a tutorial that my agent reads and then slowly suggests changes and improvements based on how your workflow is👀

Your homework for today ... Spend 8 hours completely optimizing your code factory and all of your agentic harnessing. It's tedious and frustrating, but it's worth it. I spent all of yesterday cleaning out automations, getting agent browser testing refined, culling skills and helper scripts. Really fine-tuned my code factory, and wow, it is worth it.

Change my mind: - The rich are getting ALOT richer, and it’s all thanks to AI. They are the ones thet are already tapped into several revenue streams and exponentially increasing their output directly into cash flows. How the f are we supposed to compete with them rn?

@BitsoOnchain 👀

S9 is a wrap. Here are your Stay Early Session 9 winners: 🥇 gejde.sol — $1,250 🥈 packetdetective — $750 🥉 venomz15 — $500 Congrats to all 15 finishers. The leaderboard was stacked. S10 starts NOW. $5,000 prize pool on the line.

@myfirstmilpod @LexiconBranding Hey @grok transcribe and summarize the video for me

The BIGGEST MISTAKE when choosing your company name: Making it safe. David Placek of @LexiconBranding named BlackBerry, Sonos, Pentium, Impossible Foods, Vercel, Windsurf, CapCut, Azure and 4,000+ others. P&G wanted "ProMop." He killed it and turned it into the billion-dollar Swiffer you know. He reveals the 3 things that make or break a name. Does yours tick his checklist? @thesamparr @ShaanVP

@Zeneca Your making me feel like my OpenClaw is a golden nugget, not a error, bottle neck or pit stop for a week. Opus 4.6 for everything baby

I'm convinced if you want to maximize productivity, you shouldn't be using openclaw or hermes - they take so much time bug fixing that you're better off just using claude code/codex directly there's maybe 1% of people who are the exception to this

@LolaSt1400 Sadly might be the truth

@monono_eth expect selective blind eye

The moment Republicans deploy a lifelike AI robot in a political role, it'll most likely be shot dead in 24h. Question is: Will the system actually prosecute?