Artur Schaback

What happened to Paxful during 2021-2025, and what led to its closure? Some lessons there for others. I launched @Unigox_global, built from the ground up for the web3 economy and future 🧵

Next AI psychosis unlock: AI agents write my messages in social apps, telegram, whatsapp for me. I dont have to copy paste anymore from AI to some specific messenger chat.

Most of “influencer accounts” are just larping here to promote tools of other X dudes, where they show how to start, but real stuff is not mentioned for whatever reason. Not hating, just want to share there is more than just “handing off to an ai to develop” If you really want to do proper agentic engineering, the steps are: 1. Wisprflow or @FluidVoiceApp into ur fav autistic harness - claude, codex 2. Ask to provide you html how the flow and screens would look like, with actual user flow. before final version review with opus5.5/gpt astra6 (depending which one was main model, so review with the other one) 3. Check through html, correct things, then ask to provide implementation plan that is also reviewed by another llm provider (gpt astra or opus5.5) and write the plan to @linear or whichever task tracker 4. Now the X dudes stop here because they just achieved promoting the product 5. Tell to agent to implement the plan, self review, review with opus5.5/gpt astra6 and kimi k3.1 until serious issues are fixed (!important) For 2ndary reviewers i use in order for whichever i still have weekly quota left in following order (based on intelligence): gpt astra6, opus5.5, kimi k3.1, grok4.7, gemini argon, deepseek v4 pro, muse wonder As you might know llms may not see whole codebase, so reviewing with llms that have fresh context will catch bugs and spot corner cases. Usually 2-3 round of reviews. 6. ! important. In the same prompt in point 5 also tell to test feature end to end and click through in browser/app and make screenshots as proof that it works as intended. Now the feature is ready and tested for real. Reviewing the code by multiple agents and agent clicking through actually built functionality is something that actually makes agentic engineering work where ur app doesnt break after first version. This is basic, but also there are more things you can do like some e2e tests to core functionality so agents wouldnt break it. You can have various triggers with .md files like update public docs after each release, pass the context down the line in your AI org to other agens like social media posts, leads updating. there are no limits to what other agents could do once the feature is live. Also once u have 3+ agents working at the same time, your bottleneck becomes CI/CD but how to optimize that is for next time!

title: SECURITY CAMERA FOOTAGE | Thief stole a 2,400-euro graphics card right off the store counter bro stole some low end graphics card, he is able to generate only some highly quantized slop delfi.ee/artikkel/120623503/…

agents can write code, ship apps, run your inbox. most of them still can't pick up a phone. we open-sourced 13 phone skills that work in grok bot, claude code, cursor, codex, openclaw and hermes. one install and your agent can book the table, move the appointment, chase the refund. try it and tell me what breaks

Prices got hacked too?

Bro decided to build his own blockchain as he had his conviction and not just an engineering toy. Every accelerator or vc would have told “what is your ditribution strategy and blockchains are commoditized, why are you trying to build own blockchain, there is already gmx on arbitrum”

Find some work routine that has best ratio on time spent/calories burned. Including the time to commute to gym and back. My upper right shoulder was hurting for obvious reasons of full day static position. I found VR and game @weareFitXR on @Meta @MetaQuestGaming quest 3. 30 min of workout at home about 400-500 calories burned, plus throw on top some Thrill of the Fight for actual boxing where your core trains even better and street workout routines, you save insane amount of time commuting back n forth from gym. Your shoulder and upper back pain will never come back due to the constant boxing moves you’re doing.

This is the way. You maximize your environment for that. Especially now with agents that you can hyperwork. And im talking like daily stuff, i.e 1. Go to office to do work so you don’t get distracted in home offixe. 2. Set up multiple screens in agentic era, treat agents like your employees so the always visible screens show which agent has finished its work and needs your attention 3. @AlexHormozi says write down every 15min what you did last 15min. I’ve seen and heard how other people are actually less productive with agents, as they are still working singlethreaded but slower - you give agent work to do, you go off watch youtube. Agent has finished but you keep watching youtube. The goal is to always do some productive work so you never fall back to watching something while agents are working. Any free moment you gave all agents work to do, you have to do something, give attention to other agents or learn/try something new. Youtube does not count as the ratio to spent time watching it and learning new things is worse. Best is to to it at your own pace like use @mattpocockuk learn skill that sets up you custom learning course for you at your pace for any topic in claude 4. Setup work environment when you’re on the go. Even when you’re not behind computer, you should still control agents and have visibility into them, or utilize personal ai assistants like @bot that can do so much for you. No xp wasted. Statistically you have to be always on and work all the time including weekends like revolut founder says So saying “my brain is fried” after working with multiple agents is not an excuse but should be considered normal so you feel less and less exhausted from such hyperwork.

My RAM!

Stolen eth and btc is good longterm for their price as these stolen assets will never come back into circulation.

“Funds aru safu”