Spec Driven Development != Vibe Coding digitalspeed.co.uk/articles/…

free and open source reverse engineered adobe products getartcraft.com/apps

For those wondering: Grok app > Settings > Customize Grok

This guy re-created all the adobe apps with opus-5.5, ported them to rust, and opensourced them something really cool is happening

Introducing OpenSource Clay killer - 85% cheaper than clay - Most accurate on people-search bench - 25x faster - Run GTM directly in claude code or codex Try it at treg.to/people-search Repo link below 👇

Introducing EmbeddingGemma 2! 🚀 Our lightweight, multimodal embedding model maps text, code, images, video, and audio into a single, unified embedding space. Optimized for on-device use cases, it features: - 740M parameter form factor with modular encoders - Flexible dimension sizes (768dim-128dim) via Matryoshka Representation Learning (MRL) - 8K context window (4x larger than text-only EmbeddingGemma) - A commercially permissive Apache 2.0 license

We are proud to introduce our new product, VMPal.com It is a Virtual Machine specifically designed for Apple Silicon and AI Agents. This is our very first release, and it fully supports macOS, Windows, and Linux with GPU acceleration. - Liquid Glass, - GPU Accelerator. - MCP for AI Agent on your Mac or inside the VM.

defaults write -g ComputerUseAllowForbiddenTargets -bool YES

IQ maxxing is very simple when you have the right habits: 1) think through what you need to do that day, so you act intentionally 2) do one cognitively hard thing daily: coding, math, writing, building, or whatever is tied to your real goals 3) build things with feedback loops and let reality correct you 4) write every day to force yourself to articulate thoughts precisely 5) read smart minds, then reflect and write instead of just consuming 6) make predictions + review them. it trains calibration instead of hindsight 7) protect your attention, exercise, and sleep properly it's mostly about designing your life around your brain getting constant reps + feedback. you get smarter by thinking, being wrong, and iterating.

Codex tip: once GPT-6.1 Sol is your main model, stop running Astra on every turn put Astra on call as an architect agent GPT-6.1 Sol keeps writing the code Astra only gets spawned at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Astra reviews. Sol ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split - the full tree > GPT-6.1 Sol on high runs the main session > explorer reads the code on Luna > worker edits and runs tests on Sol > researcher pulls the docs on Luna > all three on medium > Astra on call as the architect > auto_review checks every approval paste the tree and this prompt into Codex ↓ "Rebuild my Codex setup around this tree: 1. Check ~/.codex/agents and .codex/agents for agents that already fit explorer, worker and researcher. > Draft new TOML files only for missing roles > explorer and researcher on gpt-6-luna, worker on gpt-6.1-sol, all with model_reasoning_effort medium > Add an architect agent on gpt-6-astra, model_reasoning_effort high, whose only job is reviewing plans, repeated errors and finished work > Skip any that pin a different model and list them 2. In ~/.codex/config.toml set model to gpt-6.1-sol, model_reasoning_effort to high and approvals_reviewer to auto_review 3. Find anything that would override this (active profiles, flags in my shell aliases, agents.default_subagent_model). Report it, change nothing 4. Add one rule to AGENTS.md: spawn the architect before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳ developers.openai.com/codex/…

Hermes Agent can now control an actual iPhone. 📲 Not a simulator. A real, physical iPhone. The new 0bull plugin just landed in the Hermes catalog. Hermes can: see the screen read on-screen text tap type run device commands execute macros And here’s the wild part… It can publish videos to TikTok and YouTube Shorts through the apps on the phone. hermes plugins install 0bull AI agent → real iPhone → real apps. Yeah. I need to demo this. 🪽

1. You are not your thoughts. Thoughts show up on their own. You didn't pick the next one, and you can't stop them at will. If you can watch a thought arise and pass, the watcher isn't the thought. 2. Everything changes, and nothing lasts. Anything you treat as permanent was always going to surprise you. 3. Suffering comes from resisting that. Nothing lasts forever, fair or unfair. Most of the suffering is in insisting it should. 4. Everything is connected. Just as the ocean waves, the universe peoples. 5. What's left when you stop resisting is something like love. Love isn't something you add. It's what's left when you stop comparing, judging and wishing things were different. 6. There's no separate self doing any of this. The self is a story. You're not a thing. You're something you keep doing. So you can always do it differently. If you think you're a fixed thing, someone calling you "lazy" feels like an attack on who you are. If you see yourself as something you're doing, you can change what you do and there's nothing to defend. 7. Go back to ordinary life. You don't need a retreat for any of this. You need a Thursday.

Introducing Emulate-1 A new undetectable AI model trained on how humans naturally write, removing AI slop and producing more authentic, human-sounding text. I ran Emulate's outputs through Pangram, one of the stricter AI detectors. They came back as human nearly every time

OpenClaw deleted around 400k LOC of its own tests without much change in code coverage. Modern models just love writing tests for every tiny change, even if they aren't useful. This skill helped. github.com/openclaw/openclaw…

Introducing Eleven v4 and Eleven v4 Turbo, our fastest and most emotive voice models yet. Ranked #1 by Artificial Analysis.

Life satisfaction is highly consistent with personality traits. The top trait was "Have a lot of fun".

Video-use is trending again. Now it's the time to edit amazing videos. github.com/browser-use/video… Reply with your favorite video from opus 5.5.

whoever made Tailscale needs an award If you're not already doing this, you should be: If you have a PC at home, like a Mac Studio or a Mac Mini and you travel with a laptop you should always have all of the hard processing, downloading, compute, etc., done on your machine at home My 256gb Mac Studio that sits at home handles literally every single step of any hardcore processing and then reports back to my laptop I'm in a cafe in Manhattan, but my studio is still doing the hard processing for everything that I'm doing for my laptop Also, make sure that SSH and screen sharing are turned on with your laptop and your at-home machine, so if you do need to control it manually, you can do that as well And all you need is Wi-Fi for it to work properly, and it's super seamless

A CS undergrad asked me where he could have most effect in the AI age. I said probably at either extreme: either close to the technology, actually making LLMs, or close to the customer, using AI to give them exactly what they want. Or maybe both if you can stretch that far.

introducing Space: the infinite filesystem once mounted you can: → stream files to your laptop → work directly in the cloud (no downloads needed) → use your files natively with any app or agent → share a Space drive between all your computers and team try it for yourself today

It's pencils down, people. Writing code by hand is no longer an economically viable skill for most programmers at most companies. But the future of making software has never been brighter. Don't you dare black pill this beautiful moment! youtu.be/vDjW_dRyKXY?si=6Fsf…