We've noticed people sending out phishing links in DMs and comments. Quick PSA to keep everyone safe. ---- 🛑 THE RULE If someone you don't recognize is sending you links, asking for money, asking for login info, or telling you to "claim a prize" outside of an official competition post, it's not us. Don't click. Don't reply. Just delete. ---- 💰 HOW WE ACTUALLY HANDLE MONEY We will never send you money out of the blue. The only time you'll hear from us about money is if you've won a competition. When that happens, Sonija is the only person on our team who will reach out to collect your payment info to send your prize. If anyone else DMs you asking for payment details, banking info, or "verification" to release a prize, it's not us. Report it!! ---- 🚨 IF YOU GET A SUSPICIOUS MESSAGE 1. Don't click any links 2. Don't reply 3. Screenshot it if you can 4. Send the screenshot to Jake, Matt, or a mod so we can deal with it We're going to keep this community a safe place to build and learn. Thanks for looking out for each other. 🙏

If you've ever had a great conversation with an AI assistant and watched all that context vanish the next morning, you know the problem. Models forget. Every session started from zero. We have all been there and we have either use prompts, handoff documents, and structured workflows. Or some mix of the three. I needed my AI to truly know my development environment. So, I built the structure of all three into the memory system. Not just the code, but the cohesion, not just the functions, but the impact. I've spent the past several months building a fix. It's called D.R.E.A.M.S, Deep Retention & Encoding AI Memory System, and I just put up an interactive breakdown of how it works. Overview @ DREAMS, Deep Retention & Encoding AI Memory System What it is, in one paragraph: DREAMS is a persistent memory layer for AI assistants, modeled on how biological memory actually works. Inputs flow through an encoder, sit in a working buffer, get evaluated by a consolidator, and graduate to long-term storage based on emotional weight and reinforcement, not just recency. Six memory types (episodic, semantic, procedural, emotional, contextual, perspective) get encoded, retrieved, and weighted differently. Memories are permanent. Append-only by design. Recall finds them forever. The non-negotiable: Your memory, in your database. DREAMS writes into a database instance you control. Not a vendor cloud. Not a black box. The corpus you build is yours. The continuity, the lessons, the perspective, the entire graph of associations, you take it with you. Any model that can call MCP can read it. Models will change. Your continuity won't. What you can do on the site: - Step through the live architecture, click each stage to see what it does - Read the six memory types and what each one is for, hover any card to see it in action - Type into the simulator and watch a memory encode, consolidate, and promote to long-term storage in real time - Run semantic recall against a seeded library of fifty memories from the build itself

to be honest ive been dealing with an insane amount of imposter syndrome i don't think i'm the only one and i think that's why i wanted to write this. I used AI for the first time 13 months ago. At the time I was doing online auctioning for pokemon cards on whatnot, and heard that AI could code scripts. perfect, i thought... We were having a problem with meat-brains not being able to clear bid slots fast enough for a game we created. but a simple grease monkey script i wrote fixed everything and i'm not joking when i say this: it changed my life. I immediately understood the gravity of what i was using. not because i knew exactly where it was all going but because i felt it from there i did what any sane person would do. content farm then i started using it to mix music then i started using it to sell web services then i started using it to make animations voice controlled screen edits for the live streams then the vibe-code bug hit i built janky memory systems terrible harnesses fugly orchestrations i ran the gambit i was obsessed i stayed up to date on every model and every tool i remember when skills dropped and i understood the implications but the understanding was ephemeral a feeling in my gut that i couldn't articulate until i stumbled upon Jake and suddenly this system started connecting the dots it made that feeling tangible it gave the thoughts a home to be refined but the reason i'm writing this is this: ai is destroying the barrier of entry for so many things that's fine and dandy but if you're already excellent at something it can truly change the entire way you work and i think that’s the part i keep coming back to in preparation for a meeting with jake to build a workflow i really have been trying to get my ducks in a row not just “what can i automate” but where does automation actually fit into my musical workflow where does it help where does it get in the way where am i over-engineering where am i avoiding the dirt

I didn't see a post about this, maybe I missed it. I need to upgrade from my Air because while it was adequate before, now that I'm working more it's just too slow and full of files. Would love some ideas on how you're using a mac mini in your workflow - what specs did you buy, what display and are you running claude code, ollama or something else?

A few months ago, I had an idea for a build. Thanks to @Jake Van Clief 's folder architecture I succeeded. I built the thing! But then someone had a question about what I had built that turned out to matter more than I expected: are the things I built actually agents? I'd been calling them that out of habit. Then the question forced me to be precise, and being precise changed the design. Sharing the three things that came out of it, because I was being loose with the word, so I post as a cautionary tale based on all the hype around "agents" right now. 1. "Agent" in 2026 means an autonomous reasoner — establishes its own path, it adapts, it learns. But there's an older meaning: a thing that acts — that has a scope, runs different types of operations, produces different effects. My things are the second kind not the first. They can't learn, can't self-modify, can't pick their own goals. Once I admitted that out loud, I stopped saying "agent" unqualified and started saying bounded executor. That not a bad thing — it was me being honest about what I had designed. Here's the interesting thing, an autonomous agent can't be audited with certainty, because what I will do next isn't predetermined. A "bounded executor" can. I removed the autonomy feature, on purpose! If you're building "agents," ask yourself which of the two words you mean, the answer changes what you can promise about them. 2. Test for drift with identity, not observation. "Drift" changes quietly over time and is something most people try to monitor for: watch outputs, catch anomalies etc. I went the other way. Every component definition in my system is content addressed: it has a hash derived from its exact content. So, the drift test isn't statistical, it's binary. Same hash at time A and time B and BOOM! byte identical! Different hash > there's a recorded, authorized change I can point to. There is no third case. The idea here is to make drift unable to happen silently by fixing that thing's behavior to an inspectable definition.