Unreal Sarcastic

@InternetH0F A great person inside and out, he was one hell of a guy 😖

@fatimabashir211 None of them is average. Both are ugly retards

Average Pakistani. Vs. paj33t

i found out how to run AI models on your mac. for free. no $4,000 box. no api keys. no cloud. the machine in your bag already does it. 23 minutes. free. straight from an engineer on apple's mlx team. he laid out the whole stack in one talk: install mlx-lm, launch the server, point any agent at localhost. in the demo it built a working swiftui app from a blank xcode project in 2 minutes, then fixed a bug in it. nothing left the mac. and it replaces the thing people are paying $4,000 to feel like they have. watch it, then bookmark it ⬇️

You can now literally automate your 24 hours Obsidian + Cowork is the ultimate productivity combo watch & bookmark the video to automate your life

This found you for a reason

Anthropic's head of product for the Claude platform, on stage in Tokyo: "We give our agents the ability to dream : they inspect their own previous trajectories and identify how to self-improve." memory + skills + dreaming + outcomes. the actual self-improving stack, demoed live this week. [if i had only 2 days to set it up from zero:] → watch the managed agents section of the keynote (minute 21–30). free. → give your agent file-based memory: one folder, plain markdown, read it before every task → do one workflow by hand, then turn the transcript into a skill. that's the skills layer. → schedule a nightly dream pass: agent reads its own week, promotes what worked into permanent rules that's the whole stack. the creator of claude code already runs his setup this way i rebuilt it piece by piece, loops and all. save the full rebuild below ↓

Andrej Karpathy builds a personal wiki to think with LLMs. I took that idea and went further. Claude Code + Obsidian = an AI that actually knows you. Your goals. Your context. Your history. Not a chatbot. A second brain that remembers. Here's exactly how to build it:

@startnew347 Indian and Pakistani both are a community of gooners

Nowadays, a new trend has started, where Pakistani white-skinned girls are targeting the Indian public on social media to gain views and followers. Especially young Indian boys are being used for views and the word Indian is being used in the captions.

Claude Code's creator said his job is now just one thing: write loops. spoiler: most people are still trying to write the perfect prompt so i rebuilt his exact setup that he uses from scratch : every loop, every routine and every workflow so you can run it yourself. for free. save it before it disappears from your feed

Boris Cherny (Claude Code's creator) said something that stopped me cold: "I don't prompt Claude anymore. I write loops and the loops do the work. My job is to write loops." everyone clipped the line. almost nobody built what he described. so i watched all 4 minutes and rebuilt his exact his exact setup claude code + loops + a dynamic setup that runs itself. worth more than any $10,000 vibe-coding course. watch the talk. then read this. everything you need to know about loops to actually run it ↓ bookmark both. this is your weekend.

Anthropic just hired Andrej Karpathy for millions. Co-founder of OpenAI. Former head of AI at Tesla. The man who coined vibe coding. He gave out the exact blueprint so anyone can build their own ChatGPT at home. For Free In 1 hour 20 minutes , an ElevenLabs research engineer walks through the entire build on top of Karpathy's nanoGPT: tokenizer, transformer, training loop, inference. The first 10 minutes teach you more about how LLMs actually work than any university course or AI thread you'll ever read. Free Colab GPU, 15 minutes to train, and it writes Shakespeare from nothing. Watch it. Then read the full build guide below ↓

Eric Schmidt, ex-google CEO, said the quiet part out loud at Davos: "if you really want to make money, it's actually easy. found an agentic AI company." and he was specific. not a company that designs agents. one that builds an agent to actually do something. this 30-second clip is worth more than every AI thread you've bookmarked this year. agents. claude code. prompts. memory. skills. MCP. routines. learn the stack and you're early to the cheapest wealth window of the decade.

Boris Cherny (Claude Code creator): "I don't prompt Claude anymore... my job is to write loops." In his latest interview, he breaks down the setup step by step. He runs /loops + a dynamic workflow + a couple hundred agents that read his GitHub, Slack, and Twitter and decide what to build next. His only job now is writing the loops that orchestrate them. That's a multi-agent workflow. I broke down how to build your own below ↓

Garry Tan (CEO of Y-Combinator): "when someone asks how I 'prompt' my AI, the answer is: I don't. the skills are the prompts." [if I had this weekend to master skills and how to use them to automate workflows:] → read the Skillify 11-item checklist (SKILL.md in gbrain) → watch Murag + Barry Zhang: "Don't Build Agents. Build Skills Instead." → Read "Designing, Refining, and Maintaining Agent Skills at Perplexity" → do one workflow. type /skillify. watch it become permanent. that's the whole day. here is how to set it up: 1. clone GBrain (his open-source second brain, Postgres-backed memory + 30 skills) 2. add GStack (23 battle-tested slash-command skills, drops right in) 3. do anything once → type /skillify → it's a skill forever prompting is dead. skillifying is next.

Anthropic engineer: "You can build 5 assistants in one afternoon. Each one handles a task you've been doing manually every single day." this is the best way to learn to use Claude. Directly from the people who made it in this video he breaks down exactly why most people use Claude wrong ↓ why every new session starts with zero memory ↓ how memory stores let agents read and write across sessions ↓ the dreaming process that organizes memory before it grows unbounded ↓ why starting every chat from scratch is the slowest way to use Claude ↓ how Claude Projects fixes all of this without writing a single line of code if you've been starting every Claude conversation from scratch like it never met you before, you're leaving the most powerful feature untouched. agents that remember what matters to you aren't science fiction. they're already in Claude Projects. watch this instead of another scroll tonight. bookmark it before it gets buried. full guide in the article below ↓

the founder of a $20b ai company breaks down how a swarm of ai agents can replace an entire company. in one minute. for free. doesn't matter if you've never touched an agent or you've been living in claude for a year. you'll follow it. i pulled the key ideas into a practical guide for building with kimi. it's below ↓