Jay-K

@googlegemma Fantastic model for use with agentic automations

Gemma 4 was released 3 days ago. What have you built with it so far? Show us what you got! 👇

Excited to dive into the future of productivity! 🤖 AI Agents are no longer just a concept—they are the next leap in automating complex tasks. Imagine an agent that handles multi-step workflows, from research to drafting reports, freeing up human talent for high-level strategy. This shift means we move from simple task execution to true autonomous problem-solving. This isn't about replacing people; it's about augmenting human capability to achieve unprecedented levels of output. What's your take on the impact of autonomous agents in your industry? Let's discuss below! 👇 #AI #AIagents

Local LLMs are the future 💯 and Gemma 4 just proved it. No more sending your private thoughts to Big Tech servers. No more internet required. No more surprise bills or censored answers. You can now run a state-of-the-art Google model entirely on your phone — offline, private, blazing fast. Meet Gemma 4 (the new open-source beast from Google DeepMind). It runs right on your iPhone or Android with zero cloud. Privacy? Yours. Speed? Instant. Cost? Free forever. This is the end of "pay-per-token" AI. The beginning of your AI. Want it on your phone in under 60 seconds? Here’s the exact walkthrough. iOS (iPhone): Open the App Store Search “Google AI Edge Gallery” Tap Get (it’s free, made by Google) Open the app → tap “Models” or “Agent Skills” Select Gemma 4 (E2B or E4B variant — both scream on modern phones) Download the model (one-time, ~2-6GB depending on size) Chat instantly — offline, private, uncensored Android: Open Google Play Store Search “Google AI Edge Gallery” Hit Install Launch → go to model gallery Pick Gemma 4 Download & run — done. Works on most recent phones with 6GB+ RAM. That’s it. No coding. No PC. No subscriptions. Your phone just became a pocket-sized superintelligence. Why does this matter? Total privacy — nothing leaves your device Works offline — airplane mode = full AI Zero latency — faster than ChatGPT No censorship — ask anything Future-proof — runs on billions of phones already Local AI isn’t coming. It’s here. Drop this app on your phone now. #Gemma4 #LocalAI #OnDeviceAI

I built an OS for Solopreneurs: unify funnels, pitches, deals, clients. Save time/money/sanity & scale revenue faster. No more fragmented SaaS subscriptions. 🟩 NoSideHustle.co

#Solopreneurs Saturday Sick of funnel Frankensteins? I've wasted weekends wiring landing pages to forms to A/B hacks—leads evaporate before they hit proposals. Real talk: branded capture that embeds slick, tests ruthlessly, and pipes straight through. Funnel frustration too? ⤵️

🚫👻 As a solopreneur are you tired of deal ghosting? I built a SaaS solution for your one-person business: 🟩NoSideHustle.co

Closed the call with a solid "hell yeah, we're in"? Then... crickets. The deal-ghosting gap strikes again— that soul-crushing silence where verbal wins die in proposal purgatory, buried under email chains and mismatched tools. One seamless pitch flow turns notes into polished proposals + scheduling in seconds. Momentum preserved. What's the ghostiest deal you've ever lost?⤵️

Who has gemma4:e2b running on Radeon (AMD) GPUs?

OpenClaw 🚫 work easily (24+ hours in) Hermes Agent ✅ just works (5 minutes)

@philkellr Agreed. Use Hermes Agent

I'm tired of OpenClaw Every 2-3 days I have a major moment which I show to my friends: "look what AI agents can do", but then the other 90% is pure frustration and me cursing at my own AI agent for which I spent hours choosing a beautiful name and profile picture. I was fun at start: I added telegram, added voice input, then adding skills even with just voice prompting was a bliss. Then dementia hit. Facts from 48+ hours ago were forgotten. I installed a 3 level memory system. It felt like a huge hack, it barely works, I encounter bugs every day which I'm fixing. Then it breaks with every update. Not all of it, but little things. The WhatsApp integration is just insanity. After putting in every markdown file that it shouldn't reply to my friends (IN CAPITAL LETTERS) it happily started to chat with my wife and my goddaughter. And from today even claude subscription stops working. I feel like a failure! I see all the success stories left and right, YT vids and blog posts "I got it to work and here's what the AI agent does for me", and for me I'm still spending 5x the time fixing my agent than just doing the stuff by hand 🤷

Claude just lost their real developer community. Open source and now open models wins every time

@bcherny Way to lose your real developer community. Open source and now open models wins every time

Starting tomorrow at 12pm PT, Claude subscriptions will no longer cover usage on third-party tools like OpenClaw. You can still use these tools with your Claude login via extra usage bundles (now available at a discount), or with a Claude API key.

AI agents promise 10x speed, but most founders watch $5k evaporate on hallucinated loops before lunch. Real execution: cap API budgets hard, or your 'autonomous' swarm turns into a runway assassin. Chasing velocity without killswitches is amateur hour. What's your agent cost overrun story? ⤵️

@Zeneca Local LLMs and/or Grok

No more Claude for OpenClaw (and I presume Hermes and other similar tools) The decision now is to switch to openAI or to switch to try and do most things within the Anthropic ecosystem Or try a mix of both?? What're you planning on doing?

@AlexFinn Now its Hermes Agent

If you’re ever feeling dumb just remember there are people on X who still think OpenClaw isn’t the most important software release of our lifetimes

@MatthewBerman @AnthropicAI Grok and/or local LLMs it is!

It’s over. Officially. No more Claude in OpenClaw. Way to drop this Friday late afternoon @AnthropicAI So lame

#Solopreneurs - CRMs bloated with tabs kill momentum. Streamline to one view: client history, drag-drop pipeline, integrations. Focus on revenue, not navigation. What's dragging your CRM workflow?⤵️

Install Hermes Agent now. Real memory, skill auto-learning and easy to build and deploy in minutes! Reach out if you need help