CleverMC

@shedoesai Just build for a real use case.

How to become dangerously good at AI without wasting 1000+ hours. No useless tutorials. No fake AI gurus. No information overload. I spent weeks filtering the internet so you don’t have to. Here’s the ultimate AI learning stack for: • LLMs • AI Agents • MCP • Prompt Engineering • RAG • AI Engineering • Vector Databases 🧠 Videos LLM Introduction youtube.com/watch?v=zjkBMF… LLMs from Scratch youtube.com/watch?v=9vM4p9… Agentic AI Overview (Stanford) youtube.com/watch?v=kJLiOG… Building & Evaluating Agents youtube.com/watch?v=d5ElIX… Building Effective Agents youtube.com/watch?v=D7_ipD… Building Agents with MCP youtube.com/watch?v=kQmXtr… 🗂️ Repositories Microsoft AI Agents for Beginners github.com/microsoft/ai-a… Prompt Engineering Guide github.com/dair-ai/Prompt… Hands-On LLMs github.com/HandsOnLLM/Han… Made With ML madewithml.com LLM Course github.com/mlabonne/llm-c… 📚 Guides Google Agent Whitepaper kaggle.com/whitepaper-age… Building Effective Agents by Anthropic anthropic.com/engineering/bu… OpenAI Practical Guide to Agents platform.openai.com/docs/guides/ag… 📖 Books Building LLMs from Scratch manning.com/books/build-a-… The LLM Engineering Handbook oreilly.com/library/view/l… AI Engineering oreilly.com/library/view/a… 📄 Papers ReAct arxiv.org/abs/2210.03629 Toolformer arxiv.org/abs/2302.04761 Generative Agents arxiv.org/abs/2304.03442 🎓 Courses HuggingFace Agents Course huggingface.co/learn/agents-c… MCP with Anthropic anthropic.com/engineering Bookmark this. You’ll need it sooner than you think.

@bindureddy Models vs harnesses is a fun fight. Got Gemma 4 to outperform Opus in a broad use case this weekend.

Open-source AI is ruthlessly out-innovating the trillion-dollar monopolies. 🚀 Big labs are burning billions brute-forcing AGI on massive GPU clusters. Meanwhile, the open ecosystem is structurally forced to innovate on inference—and it's working. Look at what just happened: - DeepSeek v4 using SSDs for KV cache. - Breakthroughs like TurboQuant and Kimi K2 are aggressively compressing memory and driving the cost of intelligence to near zero. When you don't have infinite compute, you actually have to engineer better solutions. Constraints breed miracles. By solving the KV cache bottleneck, scrappy open-source builders are creating vastly cheaper and more profitable AI than the bloated closed-source giants. Hacker culture > GPU monopolies. Period.

@AiwithYasir When you wasted all your tokens on a graph visualizer..

🚨 SOMEONE JUST KILLED THE COACHING INDUSTRY a developer spent 22,000 hours building a Personal AI Operating System on top of Claude Code now anyone with a terminal can install it for FREE it knows your goals, remembers every decision you've made, and prepares your morning briefing while you sleep [ the numbers are insane ]: - hours of dev work in it: 22,000 - sessions logged: 6,000 - time saved per day: 2-3 hours - GitHub stars: 12,100 - skills built in: 45 - workflows wired up: 171 - safety hooks: 37 - cost to install: $0 [ the science is wild too ]: no embeddings, no vector databases, no AI magic you can't read every memory, decision, and context lives in plain markdown files you read it with cat, search it with ripgrep, version it with git 4 memory types compound over time: - work memory (active projects, open decisions) - knowledge memory (domain expertise, research) - people memory (contacts, companies, relationships) - learning memory (patterns, mistakes, what works for YOU) every complex task routes through a 7-step cycle: OBSERVE → THINK → PLAN → BUILD → EXECUTE → VERIFY → LEARN privacy is enforced by CODE, not prompts a hook called ContainmentGuard physically blocks sensitive data from being written outside designated zones [ the grift opportunity is even wilder ]: freelancers are already charging $500-2,000 per personal AI setup for executives, founders, and busy operators one person + one weekend = a consulting business that didn't exist 6 months ago every AI productivity app you're paying $30/month for is replaceable by 4 hours of setup work and this one repo 100% OPEN SOURCE, FREE

@sflorimm People have been doing that pretty well pre-AI too..

please stop using ai to write posts and replies it genuinely makes you look retarded

@immasiddx Wait until you hear about this thing called Gemini..

ChatGPT vs Claude weekly users. It’s not even close. 😭

@hasantoxr No way.. someone added a CLI or MCP to their social management product?

Holy shit... someone made it work that I can integrate a social media manager inside Claude It's called OmniSocials and it lets Claude draft, schedule, and publish to 10 platforms from a single command. No Hootsuite. No Buffer. No $200/seat pricing. Here's everything you need to know: 👇

@mikefutia Content is cheap, reach is expensive.

I just vibe coded a static ad generator in Claude Code that creates 100+ Facebook ads in minutes 🤯 All using the new insane ChatGPT Images 2.0 model. Upload one image of your brand or product → get 100+ brand-new ad concepts across every DR archetype, each one matched to a specific customer persona. Built 100% in Claude Code. Perfect for DTC brands and agencies who need to rapidly test mass creative statics at scale. Here's how it works: → Upload a single image of your brand or product → Add your brand kit (colors, fonts, logos) → Tool generates 10 customer personas from your brand research (Depleted Woman, Burned-Out Professional, Brain-Fogged Mom) → Pick how many concepts you want (40, 60, 100+) across archetypes — Bold Billboard, Listicle, iPhone Notes, iMessage, UI Hijack, Us vs Them, Press/Authority, Lo-Fi Sketch, UGC → Hit "Generate All" → finished ads render in seconds, each one targeting a specific persona with its own copy angle No more paying "static ad agencies" $3,000 per month. What you get: - 100+ on-brand static ads from a single product photo - Perfect product and text adherence powered by ChatGPT Images 2.0 - Persona-specific copy on every ad, no generic hooks - Iterate and scale statics in minutes instead of weeks - Reusable brand kits + persona libraries you build once and pull from forever - Every ad ships with the exact prompt and persona attached, so you can iterate instead of starting over. This is essentially a static ad agency in a box. I put together a complete playbook which includes EVERY single prompt I used to make this in Claude Code. Want all the prompts for free? > Like this post > Comment "STATICS" And I'll send it over (must be following so I can DM)

@0xPrajwal_ You might be using it wrong..

We pay $200/month for Claude just to hit the limit in under an hour what are we even paying for??💀

@Taniyatweets_ Because ya'll would find a way to complain about that too..

Why is there no middle tier between $20 and $100 for Claude and Codex? Feels like a $50 plan would instantly become the sweet spot for most users.

@OpenClawTips Mac studio 96gb - Gemma 4 Just use whatever you have and get to work.

local LLM people: what are you actually running right now? everyone talks like they have a DGX Spark under the desk, but I’m curious what the real setups look like DGX Spark 128GB unified memory? RTX 6000? RTX 5090 32GB? RTX 3090 24GB? MacBook Pro? Mac Studio M3 Ultra, if you somehow found one? or are you running something completely different that people are sleeping on?

@aryanlabde All of those are good at different things.. why choose?

As a vibe coder, which plan are you on right now? - $20 codex - $100 codex - $200 claude

@justbyte_ Why choose?

developers, choose one forever

@AlfieJCarter Imagine structuring this around hierarchies that are inefficient in human organizations, rather than just embracing hive mind agent fluidity.. The roles are not important, the key is shared memory and traceability on task completion, not ownership.

I've dedicated 6 weeks to building a full Claude Code GTM agent team covering every function a revenue team runs daily. 67 plugins, 92 AI agents, 52 business skills, and 19 workflow orchestrators across lead research, outreach writing, session management, context compression, and pipeline tracking - installed in 3 commands, no coding required. Here's a complete FREE breakdown for you. To access: 1. Like it 2. Comment "AGENTS" 3. Follow me (so I can send it to you via DM)

@Taniyatweets_ $20 plan? I've never run out of Max..

Dear Anthropic, please stop treating Claude Code users like beta testers Hitting limits after a few prompts on a paid plan is getting ridiculous

@AiwithYasir Benches mean nothing I guess. Output was 💩

Claude Code just got a serious competitor. Qwen Code CLI does 90% of what Claude Code does. 100% open-source. 1,000 free requests/day. And the model behind it? Only 3B active parameters but beats models 20x its size. A Thread: 🧵

@KaiXCreator Gambling.

Dear developers, is this called vibe coding?

@sukh_saroy Would rather they take care of the maintenance, updates, etc.. worth the $1400

You're paying $1,400/year in subscriptions for tools that 10 free GitHub repos already replaced. Apple, Google, Dropbox, Evernote, 1Password, Paprika, Amazon. They've all been quietly running the same playbook for a decade. Start cheap. Add features. Raise prices. Train AI on your data while you sleep. A group of open-source developers built free replacements for every single one. Better features. Zero tracking. No subscription that auto-renews after you forget to cancel. Here are 10 GitHubs that just made your subscription stack look like a scam ↓

@JayBisen473370 Can the quality be better though?

Clawdbot + Kling = 550 videos/day. No creators. No inventory. No delays. Just nonstop TikTok Shop content driving sales 24/7. Here’s the crazy part: One prompt → 500+ cinematic, ready-to-post ads. The stack: → AI builds a full UGC persona (face, voice, personality) → Arcads delivers natural voiceovers instantly → CapCut auto-edits hooks, captions & pacing → Phone farms push content straight to TikTok Shop → Cruva identifies winning hooks before production The outcome? 100+ hooks tested in days — not weeks. While others spend $5K testing 10 videos… this system finds winners and scales fast. AI isn’t just a tool anymore. It’s your entire creative team. TikTok doesn’t reward perfection. It rewards volume + conversions. And the brands posting the most? They win. Agencies are slow. Creators are inconsistent. Automation is the edge in 2026. Want the full system? Comment “SYSTEM” and I’ll send everything — prompts, tools & workflow.

@anitakirkovska Codex for building easy stuff I don't care about. Claude for building the hard stuff.

I still think Claude Code is better than Codex. prove me wrong?

@jeffscottward @Saboo_Shubham_ gpt5.5 was absolute trash for AI harness building. It looked ok until the evals.. Opus 4.7 with a couple days got me the results I wanted.

@Saboo_Shubham_ You don’t need Claude code man. And in fact I would reverse that if you really want to be sure of something I would use Codex as the final boss.

Codex /goal builds it. Claude Code /goal review and refines it. Hermes /goal manages the orchestration and handoff. All tracked on a single Kanban Board and agents keep running in the loop.