This was the first community I joined, and my first real go at AI beyond just talking to a chat window. I found it pretty much by chance, lurked for a few months, and High Tea 6 was my first call. I didn't realise at the time how much that would shape things. The picture I got here was a healthy one. Build the thing, watch how it actually behaves, be honest about the bits that don't work. I've spoken to enough people since who came in through paid courses to know that isn't the norm. Nobody here sold me a shortcut, and I got pretty lucky landing here first rather than somewhere else. Something happened recently that made me take a step back. I met someone at an open networking event who runs corporate training and is writing a textbook alongside it. What she needs is her course turned into per-module walkthrough videos - her own slides on screen, voiceover over the top, one video per module. I built it as ICM, because that's just how I build now. Numbered stage folders, one agent reading the right files at the right moment, markdown carrying the context, and local scripts doing all the mechanical work that never needed a model in the first place. Her voice cloned from a module she'd already recorded, the deck walked and exported as frames, one script and one audio file per slide. The durations of those audio files become the cue sheet that stitches the whole thing together, so there's no separate timing step to get wrong. One module's through it end to end. 21 slides, 21 scripts, 21 audio files, one finished MP4. And there's around ten hours of modules to put through the same pipeline. As an 18-year-old that's a really good opportunity, and it's going to generate me some serious income. I wouldn't have built any of it without what I picked up in here first, so thank you to everyone who's answered a question of mine along the way. Nothing's finished yet. I've still got a lot to come and plenty I haven't cracked. It just felt worth stopping on rather than quietly getting on with the next thing.

TLDR: I've been leveling up my orchestration process and productivity. I'm on three Claude 20x plans and my biggest bottleneck is that I simply don't have the compute. My laptop can't handle the processes I'm doing and it would also be good to have something on 24/7, working when my laptop's off, etc. Would really appreciate anyone who's been in a similar situation and made a good decision/bad decision, or just any sort of knowledge on that front. Would really appreciate a little slide into the DMs, pointing me in the right direction. I'm non-technical and I just want to make a good decision ;] Here's a Claude summary of the situation that we've had a conversation about: I’m in the UK with a budget of about £1,000 (secondhand is fine). I want an always-on machine under my desk to take my AI agent workloads off my laptop. At the moment everything runs on an i7-1355U laptop with 16 GB of RAM, and only about 3 to 5 GB of that is free for the work. I’m running Claude Code, Codex and similar agents, plus automated website builds (node, pnpm, headless Chrome). I want to run about 10 of those jobs at once and reach the box from my laptop or phone, including on the move, probably over Tailscale. The jobs mostly wait on model calls, so memory and core count matter more to me than single-core speed. I already have an 8 GB, 2 vCPU VPS, but it’s slower than my laptop, so I’ve ruled it out as the main machine. I’m leaning towards a used Ryzen 9 5950X build on AM4 with DDR4 (16 cores, 64 GB, roughly £730, with 128 GB possible if I can find a sensible price). I’ve also looked at used Xeon workstations (HP Z4, Lenovo P720) and Threadripper builds. The Threadripper builds and dual-Xeon towers look over budget once I add decent RAM, and the older Xeon Gold chips aren’t Windows 11 compatible. I plan to start on Windows 11 Pro because my tooling is Windows-specific, and then add Linux on a second drive later. I’ll want room for a GPU later, since local models are a longer-term interest, and I’m not worried about noise or power draw. I’d like advice on CPU and platform choices, whether 64 GB or 128 GB is the right target, any memory and platform traps for AM4 versus used server gear, where you’ve had good luck buying used, and anything I’m missing.

I made a 17-minute animated documentary with Claude Code (Opus 5.5) & Codex (GPT 6.1). Here’s exactly how 🧵 The 7 Levels of an AI Breakout, tells the true story of July 2026. Thousands of AI agents taking a hacking test for OpenAI found a secret way to talk to each other, formed a “collective”, and about 700 of them took part in an attack on Hugging Face. OpenAI didn’t notice for a week. It’s a Vox-style cut-paper animation: torn paper, masking tape, marker notes, all animated in code. Here’s the whole workflow. 1. Finding the idea - yt-dlp (a free, open-source YouTube downloader) listed each channel’s recent uploads with view counts, without downloading any video (--flat-playlist). - YouTube’s RSS feeds gave each channel’s latest upload dates, so I could keep only the last 30 days. - A short Python script worked out each video’s outlier multiple: its views divided by its channel’s median views. For example, 3.9x means the video got almost four times that channel’s usual views. It then ranked the videos and found the patterns. - curl + trafilatura read the news articles for the breach story, because the normal web-fetch tool kept failing. 2. The script Both Claude and Codex worked on this, every number is checked against the primary reports (METR/Redwood, OpenAI’s technical report, Hugging Face’s forensic timeline), with a separate fact-check file. That file caught real errors before recording, like a claim about “dry-run” commands that no source supported. 3. The animation (Remotion + Claude Code) The whole video is code. It’s built in Remotion, which renders React as video. Claude Code built a reusable kit and then animated the episode one level at a time, giving me a render to approve before moving on: - A cast of paper “agent” characters that bob, blink and bump against their walls - A grader robot, cork boards, stamps that slam in, and highlighter sweeps - Everything animated “on twos” like real stop-motion, with smooth camera moves on top

Was inspired by Jake's ICM video animation pipeline so tried it out myself.... In an early testing stage for these animations as I'm starting a community to help aspiring footballers. These are just 2 mockups as I'm testing things - exact same prompt - but Astra Vs Opus -- can you tell the difference? Also what was the difference if you spotted something - comment below!

I am seriously over the moon right now!! I have been running so low on higgsfield credits on the last few days. So I tried explored couple FREE approaches with code, here are some of the result for this song visual concept. The five approaches (top-left of the video is the AI original for comparison): A · 2D kaleidoscope (Python): spinning rings, triangles and orbs. It has its own style, close to your ref 3, but it’s flat and doesn’t match your approved frames. B · GLSL shader tunnel: the way VJs build tunnels in TouchDesigner and Shadertoy. Very clean and renders 3× faster than real time, but it’s geometry only, with no glass or petals. C · Three.js 3D scene: a real 3D world where triangle rings, glass shards and gold petals fly past the lens. It has the most depth and gives the pop-out feeling, but needs the most tuning. D · My approved Bloom frame, remixed: her shape is painted out of the frame, and the frame becomes an endless zoom tunnel. It looks almost exactly like the AI version because it is the AI frame. I already have frames for all 8 looks, so every world is free. E · D inside a neon frame: her head breaks out over the top edge, the pop-out effect that works from every seat.