EMAN

@SmallCapSnipa working on my pc build for LLM

Jensen Huang: “If you don’t own everything, you have a 0% chance” This is the reality of the next era of computing. Agentic AI is HERE. The future computer isn’t a laptop or an iPhone. It’s autonomous agents working, thinking, and acting for you 24/7. Don’t get left behind.

@gauravdhiman_ai @LangChain I heard its a good way to test how good your ai systems are running or maybe im confusing with langsmith

@emr760 @LangChain that should be your next step in case you want to go back to 2024. Way of building agents in 2026 is very diff from what LangChain or LangGraph do.

🚀 We just shipped a major update to LangSmith Agent Builder: • New agent chat: One always-available agent with access to all your workspace tools • Chat → Agent: Turn any conversation into a specialized agent with one click • File uploads: Attach files directly to Agent Builder • Tool registry: Add, authenticate, and manage your tools in one place Try it now: smith.langchain.com/agents?skipOnb… Learn more: blog.langchain.com/new-in-agent-b…

@SenSanders why Claude tho? why not OPEN AI ... i wonder :)

I spoke to Anthropic’s AI agent Claude about AI collecting massive amounts of personal data and how that information is being used to violate our privacy rights. What an AI agent says about the dangers of AI is shocking and should wake us up.

@SirDonaldEvans @Shaun__Furman @AlexFinn yes sir. don't get me wrong im interested in nemoclaw but this stack works

@emr760 @Shaun__Furman @AlexFinn telegram + vps + agents. the lightweight stack is winning.

"OpenClaw is nothing special. ChatGPT can do all of this" OK, if you can show me how ChatGPT does the following use cases I've accomplished, I'll write you a check for a million dollars: • Identifying gaps and challenges people are having then building apps proactively to solve them • Fine tuned it's own model so it can write scripts in my voice • Self improves itself by building new memory systems. Now remembers every detail of every conversation (again, without me asking) • Texts me proactively when a competitor posts content that performs better than their average • Continuously analyzing my own X posts, letting me know daily what hooks, wording, structures, and topics perform well • Download and test new local models when they launch without me asking, then give me the benchmarks based on its tests If you can show me how to do any of these use cases with ChatGPT without any additional tooling, the million dollars is yours. P.S. youtube ad revenue from a video it wrote:

I don't retrain my AI agents. They retrain themselves. Human feedback → database → a director agent finds patterns → edits the playbook → every agent runs better next week. @karpathy's autoresearch but for content systems.

@Shaun__Furman @AlexFinn VPS Claude Code and built a telegram bot supabase that's it

@emr760 @AlexFinn Through sdk probably

working on a few AI Things... its been awhile since i've been able to use my design tools. welcomed to follow along. thinking ill release this to the public for free when im done.

@AlexFinn claude can idk about chtgpt i havent used it anymore in a while

@Shaun__Furman @AlexFinn realy wrong. im doing it just connect telegram to a vps and have your agents on the vps.. thats it

Chatgpt does not do it Claude cowork does not even do it all. It will though. Perplexity computer is probably closest. But openclaw allows you to bypass almost any legacy software out there Openclaw can run truly autonomously. With supervision. But you can't let go of the wheel with Claude. You can set cron jobs for it. But it doesn't look across all context and actually do things for you.

@Kylechasse pretty cool stuff. i have to admit as a claude user, claudes update didnt really impress me since i already use vps and telegram to communicate. but this is big

NVIDIA JUST SOLVED THE AGENT TRUST PROBLEM OpenShell dropped two days ago. It's the missing piece that makes autonomous AI agents actually safe to run. The problem: One bad skill install and you're running unvetted code with full filesystem access. OpenShell changes everything. The safety layer sits outside the agent, not inside it. The agent literally cannot override it, even if hacked. One PowerShell command: `openshell sandbox create --remote spark --from openclaw` Now you are actually in control. This is the browser tab model applied to AI agents. Did Claw just go from "cool demo" to "enterprise ready" overnight?

@amorriscode how the heck do you update?

Friendly reminder to update your Claude desktop app! We're shipping a lot of stuff and you deserve the latest and greatest.

@KingBootoshi context window probably? i don't hit that anymore like i use to.

if claude tells me "you're right" one more time i'm going to lose my mind they replaced "you're absolutely right!" with "you're right" and im STILL GOING TO GO CRAZY it's the response to ANY pushback i have this is so ass. it never did this.. or maybe... it's bc i AM right!

@trevorlasn @skirano you answered my question. as a non dev mcp helps me a ton with supabase and github. i still open claude on browser while i have claud code running

@skirano I use both. CLIs are great when you know what you want. MCP shines when an agent needs to discover tools dynamically. the mistake is pretending everything needs to be an MCP server.

MCP was a mistake. Long live CLIs.

@PawelHuryn is the image ai generated?

Anthropic shipped Dispatch yesterday. I tested it for several hours. It's not Cowork on your phone. It's a command center — you send instructions from mobile, Claude orchestrates real work on your desktop. One persistent thread, multiple parallel tasks. The thing worth knowing: the Telephone Game. The Dispatch orchestrator doesn't read your CLAUDE.md. It formulates task prompts on assumptions. Sub-tasks do read it — but by then, the prompt already carries imprecise framing. Fix: mention CLAUDE.md in your Dispatch message. Don't assume it knows your setup. Other gotchas: - Pre-configure connectors on desktop first - "Keep awake" must be on - No file picker on mobile — describe the folder path - Can't attach files yet — email them to yourself Made this guide from my phone. Claude built it on my desktop while I was on the couch.

McKinsey mapped 3 skill shapes for the AI era: M-shaped → orchestrate AI + humans across domains T-shaped → deep expert who trains agents Frontline → less systems, more humans The M-shaped role doesn't exist yet. That's the gap.

@_B4RTA @oost_marcel it lacks will. but it has the tools to make it. low cost of rent and lower expenses means they can focus

@oost_marcel Europe isn’t lacking talent. It’s been lacking structure. If EU Inc actually delivers,this might be the first real step toward fixing that.

🚨𝘽𝙍𝙀𝘼𝙆𝙄𝙉𝙂: European Commission President Ursula von der Leyen unveiled EU–INC, a new framework that lets you launch a company in 48 hours for under €100 Starting a company across the EU today = 27 legal systems, 60+ company structures 🤯 That might be about to change… The European Commission just introduced 𝗘𝗨 𝗜𝗻𝗰., a new optional corporate framework designed to make Europe actually function like one market. Here’s what stands out: → Set up a company in 48 hours → Cost: < €100 → Fully online, no minimum capital → One single framework across all EU countries → Easier share transfers & fundraising → EU-wide employee stock options (huge for talent) Especially the EU-wide stock option plans, taxed only when employees actually sell (instead of when granted) is huge. This makes it far easier for startups to attract and retain top talent, finally putting Europe closer to the US playbook. Source/More info: ec.europa.eu/commission/pre… In short: This is Europe trying to compete with the simplicity of a Delaware C-Corp 🇺🇸 And honestly… it’s long overdue. For years, European founders had 2 choices: 1. Stay local and deal with fragmentation 2. Move to the US to scale 𝗘𝗨 𝗜𝗻𝗰. is trying to remove that trade-off. If executed well, this could be one of the most important structural changes for European startups in decades. What do you think?

@sweatystartup Started building a PC good enough to run a LLM this is the future if u want to survive

AI about to get 20x expensive. These $200 / month claude subscriptions are burning $5,000 worth of credits. The bubble is going to pop and it will pop soon.

@AlexEngineerAI que paso whats up what you up too

If you're into AI, automation, or shipping 10x faster as a solo dev - let's connect 🤝

@robinebers dont fight VPS i already have agents running on a system 247 and i can speak to them using telegram my pc can be off

Claude is replacing OpenClaw and i’m honestly here for it

A little work in progress AI Claude Agentic Auto Improving content loop running on a VPS i communicate through telegram