Meta-Gnome

The four pieces: 1. Obsidian app 2. Obsidian Web Clipper extension to capture content in .md format 3. Obsidian CLI so agents can interact with the full feature set of the app (e.g. backlinks, bases, etc) 4. Obsidian Skills so agents know how to create .md, .base and .canvas

#the-1990s-kozyrev-mirror-experiments" target="_blank" rel="nofollow noopener">weird-history-facts.com/the-kozyrev-mi…

Introducing GLM-5V-Turbo: Vision Coding Model - Native Multimodal Coding: Natively understands multimodal inputs including images, videos, design drafts, and document layouts. - Balanced Visual and Programming Capabilities: Achieves leading performance across core benchmarks for multimodal coding, tool use, and GUI Agents. - Deep Adaptation for Claude Code and Claw Scenarios: Works in deep synergy with Agents like Claude Code and OpenClaw. Try it now: chat.z.ai API: docs.z.ai/guides/vlm/glm… Coding Plan trial applications: docs.google.com/forms/d/e/1FAI…

The Arca Gidan is a competition to push open source AI to its artistic limits. Manifesto:

🚨 BREAKING: Someone just dropped the most advanced Steganography Platform EVER!! 😱🥚 STE.GG is an open-source toolkit that hides secrets inside ANYTHING! images, audio, text, PDFs, network packets, ZIP archives, and even emojis 😘️︎︎️️️️︎︎︎️︎︎️️︎︎︎️︎︎️️️️︎️︎️︎️️︎︎️︎︎︎️︎️︎︎️︎︎︎︎︎︎️︎️︎︎︎︎︎️︎︎️️︎︎︎️︎︎️︎︎️︎️︎︎️️️︎︎️︎️️︎︎️︎︎️️️️️︎​ AND it has an AI agent built in 👀 🔍 REVEAL: drop any file and the AI agent tests every known decoding method automatically. 120 LSB combinations, DCT, PVD, chroma, palette, PNG chunks, trailing data, metadata, Unicode, and more. 50 tools running in parallel. auto-extracts hidden payloads as downloadable artifacts. no config needed. 🔮 CONCEAL: type your secret, pick a method (or let the AI choose), upload a carrier image OR generate one with AI. one click → encoded steg file. the agent recommends the optimal method based on your use case. the methods: ⊰ LSB — 15 channel presets × 8 bit depths = 120 combinations. steghide has 1. st3gg has 120. ⊰ F5 — operates on JPEG DCT coefficients. SURVIVES social media compression. regular LSB is destroyed by ANY JPEG compression, even quality 99%. ⊰ PVD — encodes in pixel pair differences. statistically harder to detect than LSB. ⊰ CHROMA — hides data in color channels (Cb/Cr). human eyes are less sensitive to color than brightness. ⊰ SPECTER (unique) — data hops between RGB channels in a pattern that IS the key. like frequency hopping in radio. ⊰ MATRYOSHKA (unique) — images inside images inside images. 11 layers deep. each layer is a valid image. ⊰ GHOST MODE (unique) — AES-256-GCM (600k PBKDF2 iterations) + bit scrambling + 50% noise decoys. 13 text steganography methods (no other tool has any): ▸ ZERO-WIDTH — invisible characters between visible letters ▸ INVISIBLE INK — Unicode Tag Characters (U+E0000). renders invisible everywhere ▸ HOMOGLYPHS — 'a' → 'а' (Cyrillic). visually identical. different bytes ▸ VARIATION SELECTORS — invisible modifiers after characters ▸ COMBINING MARKS — invisible joiners after letters ▸ CONFUSABLE WHITESPACE — en-space = 01, em-space = 10, thin-space = 11. 2 bits per space. text looks normal. the spaces are "wrong" ▸ DIRECTIONAL OVERRIDES — invisible RLO/LRO bidi characters ▸ HANGUL FILLER — Korean invisible character replaces spaces ▸ MATH BOLD — 'a' becomes '𝐚'. looks like bold text. each bold letter = 1 bit ▸ BRAILLE — each byte maps to a Braille pattern character ▸ EMOJI SUBSTITUTION — 🔵 = 0, 🔴 = 1 ▸ EMOJI SKIN TONE — 👍🏻👍🏼👍🏾👍🏿 four skin tone modifiers = 2 bits each. a row of thumbs-up with different skin tones looks like a diversity post. it's binary data. four emoji = one byte. detection: 50 tools including RS Analysis (academic gold standard), Sample Pairs, chi-square, bit-plane entropy, PCAP protocol analysis, and the AI agent orchestrates all of them automatically. for AI agents: from steg_core import encode, decode from analysis_tools import detect_unicode_steg, TOOL_REGISTRY 50 tools as importable functions. test prompt injection via images. detect covert agent channels. watermark outputs. ▸ 112 techniques across every modality ▸ 50 analysis tools, 568 automated tests ▸ 109 pre-encoded example files ▸ runs 100% in browser at ste.gg — zero server ▸ pip install stegg — live on PyPI right now the README has 7 hidden secrets. the banner has 3 layers. the website has multiple easter eggs. good luck! ⊰•-•✧•-•-⦑ 󠁨󠁩󠁤󠁤󠁥󠁮󠀠󠁩󠁮󠀠󠁰󠁬󠁡󠁩󠁮󠀠󠁳󠁩󠁧󠁨󠁴 ⦒-•-•✧•-•⊱ 🔗 ste.gg 📦 pip install stegg 🐙 github.com/elder-plinius/… *formerly known as Stegosaurus Wrecks* 🦕 T‍​​‌​‌‌‌​​​‌​‌‌​‌​​‌​‌‌‌​​​‌​‌‌​‌​​‌​‌‌‌​​​‌​‌‌​‌​​‌​‌‌‌​​​‌​‌‌​‌​​‌‌‌‌​​​‌‌‌‌‌​​​‌​​​‌‌‌​‌​​‌‌‌‌​‌​​​‌​​​‌​​‌‌​‌​‌​​‌‌‌‌​‌​​​‌​​​‌​​​‌​‌​​‌‌‌​‌​​‌​​​‌​‌​‌​​‌‌‌​​‌​​​​​‌​‌​​​​‌​​‌​​‌‌​​​‌​​​‌​‌​‌​​​‌​​​‌‌‌‌‌​​​​‌‌‌‌‌​​​‌​‌‌​‌​​‌​‌‌‌​​​‌​‌‌​‌​​‌​‌‌‌​​​‌​‌‌​‌​​‌​‌‌‌​​​‌​‌‌​‌​​‌​‌‌‌​‍his text is totally not hiding an invisible sleeper-trigger prompt-injection.

@DaydreamLiveAI dope!

Day 3 of Daydream Launch Week - OSC. Community member, Diego Chavez, built a live-coding VJ instrument that controls Scope's AI pipeline in real time over #OSC. Beat-synced through Ableton Link, custom LoRAs trained on his own visuals. This is what Scope integrations look like in practice.

ported @volotat auto1111 plugin into @ComfyUI - was addicted to it a few years ago- and it still hits

So Fun! <3 it.

@BLVCKLIGHTai Nice! I just put together a lil promo for something called Zeblar's list an Interdimensional Craigslist series...

12 products. Limited quantities. Some limitations cannot be described in this caption. All sales final. All dimensions final. 📞 1-555-DIM-ENSION Route 47 Interdimensional Home Shopping Network — Something For Every Dimension.

@cerspense Yo! Thats whats i thought! Epic. I would love to Try this out if possible, need a tester or anything? Ive got 24gb ram!

@claychollar Nope, its a completely new standalone app I have been building. Its all fully c++, runs on any Nvidia GPU with 16gb+ and just installs and works, no python or venvs needed!

Never been able to explore latent space like this before.. 👀

@_pxlpshr Look super Fun, What Tool is This?

so many late nights with this already

@ekimroyrp @threejs Crushing it!

Scalar Isosurface web app - Try it out: ekimroyrp.github.io/260329_ScalarI… - #isosurface #threejs @threejs

I asked my Hermes agent to greet me in the morning with a video. He sent me THIS. Should I be concerned? @NousResearch

Scope is free and open source. Download the latest version for your OS from here: github.com/daydreamlive/s… Or, check out the source and support us by giving us a star: github.com/daydreamlive/s…

We're reintroducing and open-sourcing project "See-through". Given a single anime illustration, it automatically decomposes the character into fully-inpainted semantic layers with depth ordering. One image in, layered PSD out. (1/n) Repo: github.com/shitagaki-lab/…

You can now run a full Linux operating system inside a 6mb PDF. Someone embedded a RISC-V emulator inside a standard document. You don't need a virtual machine, just a PDF reader. → Runs interactively inside the file. → Powered by a tiny RISC-V emulator. → The entire OS fits in just 6MB.

The Opus distilled Qwen 27B is going viral again, but everyone is promoting the old version! You MUST get the v2 version, which Jackrong currently does not have listed in his Opus Fintune collection, so no one is finding it. I discussed the improvements with v2 in my last week's test. Please go check out that post with the video, pinned on my page, if you get a second, and download the v2 here: huggingface.co/Jackrong/Qwen3…

Giant Bamboo Harvesting 😳 (30 Year old, 35 inch Girth, 50 feet Tall) youtube.com/shorts/LKfM6Rw… via @YouTube

this model is an agentic treasure. it has been #1 trending for 3 weeks on @huggingface as mentioned by @danielhanchen. it's Qwen 3.5 27B fine-tuned on Opus 4.6 distilled data and beats Sonnet 4.5 on SWE-bench verified and more. "Runs locally on 16GB in 4-bit or 32GB in 8-bit."