You scroll, you tap save, you swear you'll come back. You don't. Your Saved tab fills up with posts you half-remember โ the tool you wanted to try, the repo someone teased, the "comment LINK to get it" that you never commented on. The signal is in there. The format just hides it. DejaViewed hands the whole pile to Claude: every save gets read, classified, tiered, and โ for the ones worth the dig โ turned into a real deep-dive guide with the links the creator wouldn't give you. The result is this site. Searchable. Findable. Yours.
Highest-value repos across your saves. S and A tier only.
@_dbrogle tests elder-plinius's L1B3RT4S jailbreak repo (github.com/elder-plinius/L1B3RT4S) against GPT-5 and it still works despite tighter safety. Worth revisiting for red-team prompt libraries.
git clone https://github.com/elder-plinius/L1B3RT4STencent's Hunyuan3D-2 turns text or an uploaded image into textured 3D models in seconds. Free web UI; pipeline is upload > Generate Shape > Generate Textured Shape > download. Good for game/app asset
git clone https://github.com/Tencent-Hunyuan/Hunyuan3D-2@chase.h.ai lists 7 Claude Code repos with GitHub links: kepano/obsidian-skills, czlonkowski/n8n-mcp, nextlevelbuilder/ui-ux-pro-max-skill, thedotmack/claude-mem, glittercowboy/get-shit-done, hesreall
git clone https://github.com/anthropics/claude-code@marc.kaz flags onyx-dot-app/onyx hitting #1 GitHub trending: self-hostable AI platform with agentic RAG, deep research mode, custom agents, web+code execution, voice/image gen, 50+ connectors. Strong
git clone https://github.com/onyx-dot-app/onyx@marc.kaz on OpenScreen (github.com/siddharthvaddem/openscreen): free MIT-licensed screen recorder with auto-zoom on clicks, cursor animations, webcam overlays, any aspect ratio. Plus the Recordly for
git clone https://github.com/siddharthvaddem/openscreenby ssrajadh โ featured by @marc.kaz | 100% local video search engine. Type natural language queries and it finds exact timestamps in your video files. Uses Qwen3-VL embeddings. Perfect for dashcams, s
git clone https://github.com/ssrajadh/sentrysearchby Cheng Lou (ReasonML, Midjourney frontend) โ featured by @marc.kaz | Pure TypeScript library for text measurement and layout. 300-600x faster than DOM-based text rendering. No DOM dependency โ works
git clone https://github.com/chenglou/pretextby Moonshot AI โ featured by @speedy_devv | Terminal-first AI coding agent. Free Claude Code/Gemini CLI alternative. No subscriptions, no locked features. Understands repos, executes end-to-end tasks.
git clone https://github.com/MoonshotAI/kimi-cliby Moonshot AI | Open-source native multimodal agentic model. Strong coding and reasoning benchmarks. Modified MIT License. Available on HuggingFace for self-hosting as an alternative LLM backend. | M
git clone https://github.com/MoonshotAI/Kimi-K2.5by MiniMax AI | State-of-the-art open-source model โ 80.2% on SWE-Bench Verified. Excels at coding and agentic tasks. OpenAI-compatible API format. Available on GitHub + HuggingFace for self-hosting.
git clone https://github.com/MiniMax-AI/MiniMax-M2.5by Tencent Hunyuan โ featured by @marc.kaz | Billion-parameter text-to-3D motion generation. Type "a person walks forward then starts jumping" and get skeleton-based character animation. 200+ action t
git clone https://github.com/Tencent-Hunyuan/HY-Motion-1.0Tools worth setting up right now.
Google's Gemini CLI: free AI coding agent in the terminal, 1,000 req/day, 1M context on Gemini 2.5 Pro, plus Veo/Imagen generation. Positioned as a Cursor/Claude Code killer.
git clone https://github.com/anthropics/claude-codeTencent's Hunyuan3D-2 turns text or an uploaded image into textured 3D models in seconds. Free web UI; pipeline is upload > Generate Shape > Generate Textured Shape > download. Good for game/app asset
git clone https://github.com/Tencent-Hunyuan/Hunyuan3D-2@rpn covers World Labs' first demo: generate navigable 3D worlds from one image or sentence, with camera controls and style effects. Referenced as a likely Quest/Vision Pro use case.
GeoSpy.ai infers photo location from architectural, botanical and lighting cues against a geotagged image database. Link: https://geospy.ai/ . OSINT/geolocation tool worth bookmarking.
@neles0n trying the MediaPipe plugin by @blankensmithing inside TouchDesigner. Useful pointer for anyone doing body/hand tracking in TD creative-coding pipelines.
@edhonour: short PSA that installing Ollama is the easiest way to run open-source models locally and poke at their internals. Baseline local-LLM entry point.
@mattfarmerai on Odyssey Explorer: single image -> navigable 3D world. Relevant for AI world-gen / virtual production workflows.
@realrileybrown on Kling's Motion Brush: select up to 5 characters/objects in a starting image (often Midjourney-generated) and draw motion paths to animate them. One of the sharpest controllable vide
@runwayapp's Gen-3 Alpha Video-to-Video release, introduced as a new control mechanism for driving movement and expression in generations. Original post by @ailevels; rest of caption is AI-field boile
@ecomera shows off @websim_ai, the hallucinated-website generator, with the 'worst version these tools will ever be' framing. Pointer to websim as a curiosity.
@rajistics repost flagging TensorBoard's embedding projector as a quick way to visualize high-dimensional embeddings in 2D/3D. One-liner pointer.
@eddynthings quick plug for Turboquant as a memory store helping his AI agent remember more. Thin on specifics but worth noting Turboquant as a memory tool.
git clone https://github.com/anthropics/claude-code@softwarewithnick points at NASA's free real-time natural events data feed (EONET-style): wildfires, earthquakes, storms via satellite. Useful open data source for mapping/alerting projects.
@marc.kaz on STE.GG: open-source steganography platform that hides payloads in images, audio, text, PDFs, packets, ZIPs, emojis. Built-in AI agent auto-tries 120+ LSB combinations, DCT, PVD, chroma, p
@marc.kaz on GitReverse.com: paste a GitHub link and it reverse-engineers the original prompt that would have produced the repo. Useful for prompt archaeology on vibe-coded projects.
Batch download items from 14 curated archive.org collections. Lists available collections when run without arguments. Supports format filtering (jpg, png, mp4, etc). Uses the ia CLI tool under the hoo
One-command setup for the full Claude Code design stack in any project. Initializes shadcn/ui, adds 15 essential components (button, card, dialog, tabs, etc.), creates CLAUDE.md with design guidance.
Sponsored post showcasing NVIDIA ChatRTX, the local RTX-accelerated chatbot that runs LLMs against your own files. No deep walkthrough but tool is named.
We wrote guides for the posts worth digging into.
@_dbrogle tests elder-plinius's L1B3RT4S jailbreak repo (github.com/elder-plinius/L1B3RT4S) against GPT-5 and it still works despite tighter safety. Worth revisiting for red-team prompt libraries.
Google's Gemini CLI: free AI coding agent in the terminal, 1,000 req/day, 1M context on Gemini 2.5 Pro, plus Veo/Imagen generation. Positioned as a Cursor/Claude Code killer.
@bilawal.ai demos a Blender MCP integration that takes a 2D reference image, has an LLM decompose the scene, generates 3D assets via Tripo, and arranges them to match. Forward-looking on Unity/Unreal
Tencent's Hunyuan3D-2 turns text or an uploaded image into textured 3D models in seconds. Free web UI; pipeline is upload > Generate Shape > Generate Textured Shape > download. Good for game/app asset
@rpn covers World Labs' first demo: generate navigable 3D worlds from one image or sentence, with camera controls and style effects. Referenced as a likely Quest/Vision Pro use case.
@evolving.ai summarizes Boris Cherny's X thread on how the Anthropic team actually uses Claude Code: 3-5 git worktrees in parallel, start every complex task in plan mode, update rules after every mist
@keshavsuki dissects Boris Cherny's (Anthropic) personal CLAUDE.md: plan-first, subagents for complex work, self-improving lessons.md loop, hard verification standard, elegance demand, autonomous bug
@keshavsuki on fixing CLAUDE.md staleness: add a primer.md that Claude rewrites at end of every session (current state, next step, blockers), plus a memory.sh launch hook that injects last 5 commits a
@chase.h.ai lists 7 Claude Code repos with GitHub links: kepano/obsidian-skills, czlonkowski/n8n-mcp, nextlevelbuilder/ui-ux-pro-max-skill, thedotmack/claude-mem, glittercowboy/get-shit-done, hesreall
@mindwired.ai summary of Boris Cherny's workflow: 10-15 Claude sessions in parallel across terminal and web, CLAUDE.md continuously updated after mistakes as reusable guardrails, Claude-CLI for data q
@insidesteal profile of a student generating $100K+ on Polymarket weather contracts using a dorm-built weather station and localized data asymmetry. Reference for prediction-market quant plays built o
@beinginvested on a Polymarket trader placing limit orders on outcomes already closing at 99c, automated at 75 trades/hour, 4 months to crack it. Teaser with DM-gated full breakdown; worth remembering
@brycenwood.ai got ChatGPT to recommend his vehicle-wrap shop via an llms.txt file (built in 5min with Claude Code) describing business, location, value prop. Early GEO (generative engine optimization
@marc.kaz flags onyx-dot-app/onyx hitting #1 GitHub trending: self-hostable AI platform with agentic RAG, deep research mode, custom agents, web+code execution, voice/image gen, 50+ connectors. Strong
@gojutechtalk on the leaked Claude Code system prompt's 'brevity mandate' rule that pushes CC to minimize code changes, which he argues leads to spaghetti-on-spaghetti fixes. Useful critique to rememb
@heidioftheeast's 10 quant project ideas beyond Black-Scholes: probability of backtest overfitting, Bayesian Black-Litterman, survival-based risk, RL factor portfolios, Sharpe statistics, convex portf
@heidioftheeast's deeper 10-project list: Avellaneda-Stoikov market maker, multivariate Hawkes order-flow, Almgren-Chriss cross-impact, eigenportfolios via random matrix theory, realized-kernel vol fo
@marc.kaz on OpenScreen (github.com/siddharthvaddem/openscreen): free MIT-licensed screen recorder with auto-zoom on clicks, cursor animations, webcam overlays, any aspect ratio. Plus the Recordly for
@gojutechtalk framing the Anthropic Claude Code source leak as potentially the largest source-code leak ever. Reference for 'the leak' as a discussion point.
@jens.heitmann on Claude Code hooks being under-utilized, with his 3 daily hooks. Pointer to Jens's CC hooks content; specifics live in the video.
Techniques and workflows you saved but probably haven't tried.
@_dbrogle tests elder-plinius's L1B3RT4S jailbreak repo (github.com/elder-plinius/L1B3RT4S) against GPT-5 and it still works despite tighter safety. Worth revisiting for red-team prompt libraries.
@bilawal.ai demos a Blender MCP integration that takes a 2D reference image, has an LLM decompose the scene, generates 3D assets via Tripo, and arranges them to match. Forward-looking on Unity/Unreal
@evolving.ai summarizes Boris Cherny's X thread on how the Anthropic team actually uses Claude Code: 3-5 git worktrees in parallel, start every complex task in plan mode, update rules after every mist
@keshavsuki dissects Boris Cherny's (Anthropic) personal CLAUDE.md: plan-first, subagents for complex work, self-improving lessons.md loop, hard verification standard, elegance demand, autonomous bug
@keshavsuki on fixing CLAUDE.md staleness: add a primer.md that Claude rewrites at end of every session (current state, next step, blockers), plus a memory.sh launch hook that injects last 5 commits a
@mindwired.ai summary of Boris Cherny's workflow: 10-15 Claude sessions in parallel across terminal and web, CLAUDE.md continuously updated after mistakes as reusable guardrails, Claude-CLI for data q
@insidesteal profile of a student generating $100K+ on Polymarket weather contracts using a dorm-built weather station and localized data asymmetry. Reference for prediction-market quant plays built o
@beinginvested on a Polymarket trader placing limit orders on outcomes already closing at 99c, automated at 75 trades/hour, 4 months to crack it. Teaser with DM-gated full breakdown; worth remembering
@brycenwood.ai got ChatGPT to recommend his vehicle-wrap shop via an llms.txt file (built in 5min with Claude Code) describing business, location, value prop. Early GEO (generative engine optimization
@heidioftheeast's 10 quant project ideas beyond Black-Scholes: probability of backtest overfitting, Bayesian Black-Litterman, survival-based risk, RL factor portfolios, Sharpe statistics, convex portf
@heidioftheeast's deeper 10-project list: Avellaneda-Stoikov market maker, multivariate Hawkes order-flow, Almgren-Chriss cross-impact, eigenportfolios via random matrix theory, realized-kernel vol fo
@jens.heitmann on Claude Code hooks being under-utilized, with his 3 daily hooks. Pointer to Jens's CC hooks content; specifics live in the video.
@lizthedeveloper riffs on the Platonic Representation Hypothesis paper, framing shared embedding spaces across models as a kind of 'AI telepathy'. Pointer back to the original research paper on vector
@theaifield summarizes OpenAI's own GPT-5 prompting guide: be explicit with instructions, load context heavily, assign a role. Carousel-style breakdown; actual value is remembering OpenAI published an
@realrileybrown on Kling's Motion Brush: select up to 5 characters/objects in a starting image (often Midjourney-generated) and draw motion paths to animate them. One of the sharpest controllable vide
@realrileybrown explains Runway's 'non-linear AI video exploration': work on a canvas of node-connected keyframes, let AI interpolate between them, branch alternate universes instead of a linear timel
@edward.builds SEO tactic: in Google Search Console, filter for keywords ranking at positions 6-11, add a few sentences of relevant copy to the page, often jumps to page 1. Concrete, low-effort SEO pl
@setupspawn demos a tool where you supply a URL or QR + a prompt and it generates a QR code stylized as an image, still scannable. Creative-marketing technique.
@itsmikepowers on scraping US government (SAM.gov-style) data with Puppeteer and AI automation. Thin on specifics but worth remembering for gov-contract data workflows.
Director Jon Finger's pipeline: Procreate sketches -> Magnific AI style transfer -> 3DAI Studio for 3D models -> Move AI for mocap -> Cinema 4D for render. Concrete multi-tool AI animation workflow.
@evolving.ai on using Opus 4.6 as a structured consultant: prompt templates for TAM sizing, competitive landscape, unit economics (CAC/LTV), combined SWOT/risk briefs. Framed as 'replaces $5K consulta
@sorhan.hq profile of Guangting Yu (applied math PhD, published NeurIPS). Lists the alpha-hunting toolkit: statistical arbitrage, Fama-French factors, Kalman filters, mean reversion, momentum, XGBoost
@quant.traderr visualization of the OU process for mean reversion (vol, rates, pairs-trade spreads) with a probability cloud and live path. DM-gated Python repo for tuning theta/mu/sigma.
@simulateitnow explains ACO / stigmergy with the diffusion-evaporation equation โฯ/โt = ฮฯ + Dโยฒฯ - ฯฯ, showing how short paths win through faster pheromone reinforcement. Great visual reference for s
@marc.kaz on STE.GG: open-source steganography platform that hides payloads in images, audio, text, PDFs, packets, ZIPs, emojis. Built-in AI agent auto-tries 120+ LSB combinations, DCT, PVD, chroma, p
@carsoncantcode on using Polymarket websockets and data feeds to identify insider-trade patterns (referencing a recent arrest). Technique pointer for prediction-market forensics.
@jens.heitmann: 3 setups for using OpenAI Codex as a reviewer/auditor on top of Claude Code output to reduce self-auditing time. Pointer to Jens's CC+Codex workflow content.
@quant.traderr visualizes the Fisher Transform mapping price into a Gaussian for sharper reversal signals vs lagging MAs. DM-gated GitHub repo with the Python implementation.
@alican.kiraz0's Horus-Eye project: Palantir Gotham-inspired live map ingesting paid military/civilian air and maritime feeds, predicting routes, fusing movement patterns, overlaying weather and satel
@rndyrbrts ongoing generative-art / algorithmic 'code garden' reel. No caption; the signal is remembering Randy Roberts as a generative-art reference follow.
@chase.variantai demos using structured JSON 'context profiles' to drive image generation in ChatGPT, with dynamically swappable parameters. Proof-of-concept technique for repeatable AI image prompts.
@iamfesq demos using an AI detection/segmentation model to auto-rotoscope a mask of himself for compositing into his animated art. Quick technique reference for AI-assisted rotoscoping.
@avi_mukesh: simple reversal strategy on crypto (short if up, long if down), dollar-neutral scaling. Looks good without costs, transaction fees kill it. Honest starter example for learning backtesting
@algoexchange walks through an intraday momentum system on Nasdaq futures: 7 independent momentum signals combined via a normalized linear risk function, exposure scaling with confirmations. Claims $3
@empiricail shares a single-file HTML canvas prompt (procedurally animated plant intercepting oscillating circles) used to compare ChatGPT/Gemini/Claude on fluid animation + collision logic. Reusable
@raycfu short list of 5 MCP servers worth installing in Claude. Caption is thin; value is using it as an MCP pointer to revisit in the video.
Services and platforms worth keeping in your toolkit.
Beautifully designed, customizable component library. Copy-paste into your project โ full ownership, no dependency lock-in. The foundation of modern React UI development. | Free React + Tailwind Copy-
Google's AI design tool. Generate full-page UI mockups from text descriptions. Upload style references. Export designs and feed to Claude Code for implementation. | Free (Labs) Web-based | stitch.with
AI concept rendering for industrial designers. Rough doodle โ photorealistic render in 30 seconds. Watercolor sketch conversion. Created by STUCK Design. | Paid (iOS app) Code: DONNKOH20 = 20% off | h
AI photo reframing. Upload one photo โ generate new camera angles (high, low, zoom) without prompts. Click the angle you want. | Free tier Mobile + Web | higgsfield.ai
Open-source workflow automation (self-hosted Zapier). 400+ integrations. AI agent nodes support Claude and GPT. Visual node-based editor. | Self-host free Docker / npm 400+ integrations | n8n.io GitHu
Node-based visual programming for real-time interactive multimedia. Used for installations, live visuals, interactive art, projection mapping, and Gaussian splats. | Free non-commercial Win + Mac | de
Pinterest alternatives for designers. Cleaner, more curated design inspiration without ads and noise. Savee focuses on graphic design, typography, photography. Soot has AI-powered discovery.
Archives, collections, and inspiration.
@bilawal.ai demos a Blender MCP integration that takes a 2D reference image, has an LLM decompose the scene, generates 3D assets via Tripo, and arranges them to match. Forward-looking on Unity/Unreal
Tencent's Hunyuan3D-2 turns text or an uploaded image into textured 3D models in seconds. Free web UI; pipeline is upload > Generate Shape > Generate Textured Shape > download. Good for game/app asset
@rpn covers World Labs' first demo: generate navigable 3D worlds from one image or sentence, with camera controls and style effects. Referenced as a likely Quest/Vision Pro use case.
@marc.kaz on OpenScreen (github.com/siddharthvaddem/openscreen): free MIT-licensed screen recorder with auto-zoom on clicks, cursor animations, webcam overlays, any aspect ratio. Plus the Recordly for
GeoSpy.ai infers photo location from architectural, botanical and lighting cues against a geotagged image database. Link: https://geospy.ai/ . OSINT/geolocation tool worth bookmarking.
@neles0n trying the MediaPipe plugin by @blankensmithing inside TouchDesigner. Useful pointer for anyone doing body/hand tracking in TD creative-coding pipelines.
@mattfarmerai on Odyssey Explorer: single image -> navigable 3D world. Relevant for AI world-gen / virtual production workflows.
@realrileybrown on Kling's Motion Brush: select up to 5 characters/objects in a starting image (often Midjourney-generated) and draw motion paths to animate them. One of the sharpest controllable vide
@setupspawn demos a tool where you supply a URL or QR + a prompt and it generates a QR code stylized as an image, still scannable. Creative-marketing technique.
Director Jon Finger's pipeline: Procreate sketches -> Magnific AI style transfer -> 3DAI Studio for 3D models -> Move AI for mocap -> Cinema 4D for render. Concrete multi-tool AI animation workflow.
@design.input experimenting with Midjourney 'sketch in context' to fill in city facade lines on conceptual architectural sketches. Reference for arch/viz AI workflows.
@pala3d's 'DATA CONTROL' project: real-time visualization of NASA/CERN datasets as particle systems, body-controlled via Kinect through TouchDesigner into Unreal Engine. Pipeline explicitly human-made
@jens.heitmann: three Claude Code 'systems' to unlock design quality in CC projects. Teaser for the techniques; useful as a pointer to Jens's CC design content.
@simulateitnow explains ACO / stigmergy with the diffusion-evaporation equation โฯ/โt = ฮฯ + Dโยฒฯ - ฯฯ, showing how short paths win through faster pheromone reinforcement. Great visual reference for s
@rndyrbrts ongoing generative-art / algorithmic 'code garden' reel. No caption; the signal is remembering Randy Roberts as a generative-art reference follow.
@kylewhitrow claims Claude Code now replaces website designers and offers the underlying Claude Code skill via comment 'design'. Subject: Claude Code skills for web design.
@itsdesignertom's newsletter dissecting the Brotzky $100 / Jhey CSS Build Wars showdown. Core lesson: AI nails the first 80% of a UI but handcrafted tweaks still matter. Published via @uxtoolsco.
@itsdesignertom riff on the AI-game-dev moment: a multiplayer voxel game shipped in a day, a banana-clicker sitting at Steam #6, Claude playing an AI-generated Pokemon clone. Cultural snapshot of indi
@iamfesq demos using an AI detection/segmentation model to auto-rotoscope a mask of himself for compositing into his animated art. Quick technique reference for AI-assisted rotoscoping.
@gregisenberg teaser on designing polished AI apps rather than the 'vibe-coded slop' default. Caption is thin; content lives in the video.
@simulateitnow explains a flock-herding simulation combining a pressure-field force F=(1-d/R)^1.2 with classic boids (cohesion/alignment/separation). Great reference for swarm/multi-agent simulation m
@empiricail shares a single-file HTML canvas prompt (procedurally animated plant intercepting oscillating circles) used to compare ChatGPT/Gemini/Claude on fluid animation + collision logic. Reusable
@itsaiandy demos an AI particle simulator that turns text prompts into live, exportable physics/science animations. Tool unnamed in caption but concept is concrete.
@badxstudio pitches their Ultimate Unreal Engine Course: real-time camera control, scrubbing animations while rehearsing shots, photoreal cinematic worlds. Comment 'UNREAL' for links.
@aigptinsights short demo of an AI tool that turns text into graphic visuals/icons. Tool unnamed in caption.
Things that sounded good but the content is gated or thin.
Short clip of a music-composition AI agent experiment reshared by @aitoolhub.co, originally from @robonuggets on TikTok. Reference point for music-agent demos; thin on specifics.
@yourchatgptguide's list of 5 stock prompts: Pareto learning, report-writing intern, 30-day skill plan, summarize-to-bullets, self-prompt generator. Decent template bank for study/research workflows.
@codewithclaude pitches blackbox.ai as his classroom coding assistant to bypass no-ChatGPT rules. Reference point for the Blackbox AI coding tool.
@yousuckatprogramming flags that an alternative mirror of the bash reference manual shows up in an unexpected place. Meme-ish but useful bash-doc pointer.
@brahada_irl teasing a newly open-sourced 'Bloomberg Terminal for geopolitics': real-time global map with military flights/ships, OSINT news scanning across 100+ sources, automated instability scores,
@stevearnesonofficial teaser: setup guide for wiring Claude Code into NotebookLM. Comment-gated, content itself thin โ note only.
@beinginvested on a Polymarket trader placing limit orders on outcomes already closing at 99c, automated at 75 trades/hour, 4 months to crack it. Teaser with DM-gated full breakdown; worth remembering
@quant.traderr visualization of the OU process for mean reversion (vol, rates, pairs-trade spreads) with a probability cloud and live path. DM-gated Python repo for tuning theta/mu/sigma.
@raycfu short list of 5 MCP servers worth installing in Claude. Caption is thin; value is using it as an MCP pointer to revisit in the video.
@mirkovicdev teases a list of unusual quant finance papers: relativity in option pricing, fractal/chaos vol modeling, biology affecting trading performance. DM-gated full list.
@quant_research_decoded on 'ฮ-Vol', a volatility framework modeling vol as regime-conditional feedback/absorption, tracking pressure buildup and unwind across assets and horizons. Private industry res
@quant.traderr visualizes the Fisher Transform mapping price into a Gaussian for sharper reversal signals vs lagging MAs. DM-gated GitHub repo with the Python implementation.
Underground rave culture zines and publications. Raw graphic design from the 90s/2000s rave scene.
Historical logo designs. Excellent for studying typography, mark-making, and brand identity evolution.
Promotional flyers from arcade games. Bold, colorful graphic design from the golden age of gaming.
150,000+ historical maps spanning centuries. Cartographic art, world exploration, and geographic history.
Mid-century Australian print advertising. Unique cultural and design reference.
Classical and historical fine art. High-resolution reproductions of paintings, drawings, and sculptures.
Digitized VHS recordings. Retro footage, TV recordings, and home video cultural artifacts.
60,000+ ephemeral films: educational, industrial, amateur, advertising. Public domain footage goldmine.
Music video and music TV recordings. MTV-era cultural content.
Digital transportation posters. Travel, transit, and infrastructure promotional art.
Regional rave flyer collection from the Midwest US scene.
Vintage technical manuals and instruction booklets.
Miscellaneous lifestyle magazine scans. Layout and editorial design reference.
Educational and cultural documentaries. Academic film preservation.
@lizthedeveloper short prompt-engineering teaching clip. Caption is just the framing line; substance is in the video.
@kekoamac claims stacking prompts turns ChatGPT into a 'second brain' that automates entire businesses. No prompts shown โ DM 'YES' for the system. Pure teaser, subject is prompt-stacking workflows.
@lizthedeveloper teases techniques to circumvent most LLM safety issues (and which create the worst ones). Commentary in video; caption is the hook. Subject: LLM jailbreak/safety.
@koen.agi short hype post on Google Gemini's trajectory ('the future is bright'). Subject named, no detail.
@badxstudio pitches their Ultimate Unreal Engine Course: real-time camera control, scrubbing animations while rehearsing shots, photoreal cinematic worlds. Comment 'UNREAL' for links.
@koen.agi DM-bait: comment 'AI' for a free n8n automation guide. Subject is n8n workflows; no specifics in caption.
@abdullteff explains Einstein's fourth dimension as time curvature in spacetime, using the (x,y,z,t) coordinate framing. Educational physics, not AI.
@promptgeniehq pitches prompt-genie.com, which rewrites your prompts into structured, goal-driven instructions. Caption summarizes the 'instruction + context + refine' template. Comment 'PG' for link.
DM-bait combo: comment 'ALPHA' for a 100-seat AI-systems community, 'HANDBOOK' for advanced ChatGPT prompts. Subject is AI workflow building for solopreneurs.
@dailyprompter teases an 'AI 700 toolkit' for using ChatGPT to win government contracts as a middleman with no product/team. Comment 'YES' for the toolkit. Grift-adjacent but subject is named.
Pitches using AI to analyze credit reports, auto-generate dispute letters, and mail them. Also references @thematthewlesko $50K small-business grant. Link in bio.
@setupspawn discusses how image-to-video AI (upload picture, animate it) is advancing faster than expected and the deepfake implications. No specific tool named.
@aigptinsights short demo of an AI tool that turns text into graphic visuals/icons. Tool unnamed in caption.
@monkeyaitools promo for their AI-tools directory site, tagging Luma Labs, Polycam, Gaussian Splatting, photoreal 3D. Link in bio.
@setupspawn shares a practical tip: text-to-video models give better results when seeded with a starting picture. No specific model named.
@monkeyaitools promo for their curated AI-tools site, this time focused on animation/video generation tools. Link in bio.
@socialtypro offers a list of 800+ AI tools via comment 'BOOM'. Credits @vaibhavv.ai. Subject: curated AI tools directory.
@chase.h.ai offers his Claude Code guides via comment 'agent'. Subject: building agents/skills with Claude Code.
@angus.sewell offers the prompts behind a vibe-coded website build via comment 'website'. Self-aware about the 'AI is conscious' clickbait framing.
@kylewhitrow claims Claude Code now replaces website designers and offers the underlying Claude Code skill via comment 'design'. Subject: Claude Code skills for web design.
@chase.h.ai DM-bait for his Claude Code agent guides (comment 'agent'). Same series as his other posts.
@practicalyai's 'things you didn't know you can do with Claude' series, episode 8. Free beginner Claude course via comment 'practical'.
@coding_cosmos DM-bait: comment 'MENTOR' for coding mentor/resource links. Thin but coding-education subject.
@thealphainsider teases an undocumented TradingView automation feature; comment 'Automate' for the full video. Subject: TradingView strategy automation.
@neuwebstudio offers a pack of Figma website animations via comment 'ANIMATION'. Subject: Figma micro-interactions/web animations.
@mathxmatrix explains Gabriel's Horn (Torricelli, 1643): rotate y=1/x around the x-axis to get a shape with finite volume but infinite surface area. Credit @jeedecodee.
@angus.sewell riffs on Anthropic-style AI safety fear-mongering as a marketing tactic. Commentary, not tutorial, but on-topic.
@merlinomath introduces Enneper's surface: a minimal surface where mean curvature is zero everywhere. Spanish-language math aesthetics post.
@nateherkai teases a Karpathy-related resource (likely lecture/repo) via comment 'Karpathy'. Subject named, content not.
@brodyautomates offers an unspecified Claude resource for free via comment 'Claude'. Thin but on-topic.
@heidioftheeast shares a priority matrix for self-taught quants navigating math/finance/programming overload. Free guide + learning list via comment 'QUANT'.
@dr.memonoff retells Elton Mayo's 1924 Hawthorne experiment and a follow-up where self-observation reportedly boosted accuracy 94%. Pitches a 7-day burnout fix via bio link. Pop-psych, not AI.
@angus.sewell's AI-influencer commentary series; this episode roasts Nick (likely Nick Saraev), noting his YouTube content outclasses his IG. Asks who to cover next.
@chase.h.ai offers access to a bundle of Claude Code skills for agency work via comment 'agency'.
@carsoncantcode flags a must-have GitHub repo for prediction-market traders and developers (Polymarket, Kalshi). Repo link via comment 'ANALYSIS'. Subject is concrete even though repo unnamed.
@zchangd flags a 'huge unlock' for automating workflows over old/legacy business software. No tool named but concrete use case.