AI Saves, Vol. 1

AI Saves, Vol. 1 holds 57 saved posts from 44 creators, saved between 2023-08 and Februar (7 S-tier, 25 A-tier, 23 B-tier, 2 C-tier). The most-tagged tools are ChatGPT, Claude, Anthropic, Google and Runway. Most-saved creators: @lizthedeveloper (3), @mattfarmerai (3), @setupspawn (3). 4 curated guides draw 3+ entries from it, starting with The One-Person Video Studio: AI Tools That Replace a Production Team, Napkin Sketch → Production Asset: The 5-Tool Creative Pipeline, Escaping the AI House Style — Taste Trained on the Public Domain.

Guides built from this collection

All 57 entries · best first

  1. SL1B3RT4S — Pliny jailbreak prompts still landing on GPT-5@_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…@_dbrogle · 2025-09-06 · repo
  2. SBypassing 90% of AI guardrails — @lizthedeveloper@lizthedeveloper teases techniques to circumvent most LLM safety issues (and which create the worst ones). Commentary in video; caption is the hook. Subject: LLM…@lizthedeveloper · 2025-07-18 · inspiration
  3. SGemini CLI — free terminal coding agent, 1K req/day, Gemini 2.5 ProGoogle'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…@davi.d_roberts · 2025-07-05 · tool
  4. SHunyuan3D-2 — Tencent's free image-to-3D model generatorTencent'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 >…@nick_saraev · 2025-04-15 · tool
  5. SBlender MCP + Tripo — 2D reference image to full 3D scene@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…@bilawal.ai · 2025-03-25 · technique
  6. SWorld Labs — explorable 3D worlds from a single 2D image@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…@rpn · 2024-12-02 · tool
  7. S5 ChatGPT learning prompts — 80/20, intern mode, skill plan@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…@yourchatgptguide · 2024-07-07 · skill
  8. ABlackbox AI — coding assistant as 'Google search for code'@codewithclaude pitches blackbox.ai as his classroom coding assistant to bypass no-ChatGPT rules. Reference point for the Blackbox AI coding tool.@codewithclaude · February 2 · tool
  9. AGeoSpy.ai — geolocate any photo from buildings, plants, shadowsGeoSpy.ai infers photo location from architectural, botanical and lighting cues against a geotagged image database. Link: https://geospy.ai/ . OSINT/geolocation tool…@innovation · 2025-08-13 · tool
  10. APlatonic Representation Hypothesis — embeddings as AI telepathy@lizthedeveloper riffs on the Platonic Representation Hypothesis paper, framing shared embedding spaces across models as a kind of 'AI telepathy'. Pointer back to the…@lizthedeveloper · 2025-05-22 · news
  11. AOllama — run open-source LLMs locally to learn how they work@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.@edhonour · 2025-05-03 · skill
  12. AGoogle's comprehensive prompt engineering guide — PDF recap@aitoolhub.co reshares @robonuggets's recap of Google's own prompt engineering guide, pitched as the most comprehensive from a major lab. Pointer to the Google…@aitoolhub.co · 2025-04-15 · skill
  13. AQwen 2.5 Max, Wan 2.1, Lumina 2 — China's open-source trio@nick_saraev walks through three open-source Chinese AI models: Qwen 2.5 Max (chat/code/search/image/video), Wan 2.1 (open-source video gen), and Lumina 2 (photoreal…@nick_saraev · 2025-04-14 · tool
  14. AMediaPipe TouchDesigner plugin by @blankensmithing@neles0n trying the MediaPipe plugin by @blankensmithing inside TouchDesigner. Useful pointer for anyone doing body/hand tracking in TD creative-coding pipelines.@neles0n · 2025-01-29 · demo
  15. AOdyssey Explorer — turn any image into an explorable 3D world@mattfarmerai on Odyssey Explorer: single image -> navigable 3D world. Relevant for AI world-gen / virtual production workflows.@mattfarmerai · 2024-12-23 · tool
  16. ARunway non-linear video — node canvas of AI keyframes@realrileybrown explains Runway's 'non-linear AI video exploration': work on a canvas of node-connected keyframes, let AI interpolate between them, branch alternate…@realrileybrown · 2024-12-03 · technique
  17. AKling Motion Brush — direct up to 5 characters in one AI video@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…@realrileybrown · 2024-12-02 · tool
  18. ANemotron 70B — NVIDIA's open-source LLM benchmark leader@mattfarmerai flagging NVIDIA's Nemotron 70B as (at the time) the best open-source LLM. One-line pointer, no deeper analysis.@mattfarmerai · 2024-10-19 · tool
  19. AMonkeyAITools directory + Luma Labs/Polycam tags@monkeyaitools promo for their AI-tools directory site, tagging Luma Labs, Polycam, Gaussian Splatting, photoreal 3D. Link in bio.@monkeyaitools · 2024-10-10 · tool
  20. ARunway Gen-3 Alpha Video-to-Video — precise motion control@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…@ailevels · 2024-09-15 · tool
  21. AText-to-video tip: start from an image — @setupspawn@setupspawn shares a practical tip: text-to-video models give better results when seeded with a starting picture. No specific model named.@setupspawn · 2024-07-29 · inspiration
  22. AKling AI — free international rollout of text-to-video@mattfarmerai news beat on Kling AI going international with free video generation. Reference for when Kling became accessible outside China.@mattfarmerai · 2024-07-25 · tool
  23. ALlama 3.1 — 8B / 70B / 405B open-source release@only_agis_ recap of the Llama 3.1 launch: 8B, 70B, and 405B open weights, topping evals at the time. Reference point for 'when open-source caught frontier'.@only_agis_ · 2024-07-24 · tool
  24. AStriking-distance keywords — GSC SEO tactic (positions 6-11)@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…@edward.builds · 2024-07-06 · technique
  25. Awebsim.ai — hallucinated websites as an AI tool demo@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.@ecomera · 2024-07-05 · demo
  26. AVeo — Google's text/image/video-to-video model (Google I/O)Official @google reel introducing Veo at Google I/O: high-def video generation from text, image, and video prompts. Reference for Veo launch.@google · 2024-05-15 · technique
  27. AAI-styled QR codes — generate codes that look like images@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.@setupspawn · 2024-04-24 · technique
  28. AScraping SAM.gov — puppeteer + AI for government data@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.@itsmikepowers · 2024-04-20 · technique
  29. ASketch-to-3D-anim pipeline — Procreate + Magnific + 3DAI + Move AIDirector Jon Finger's pipeline: Procreate sketches -> Magnific AI style transfer -> 3DAI Studio for 3D models -> Move AI for mocap -> Cinema 4D for render. Concrete…@chatgptricks · 2024-04-16 · technique
  30. ANVIDIA ChatRTX local LLM — @nathanespinozayt sponsored demoSponsored post showcasing NVIDIA ChatRTX, the local RTX-accelerated chatbot that runs LLMs against your own files. No deep walkthrough but tool is named.@nathanespinozayt · 2024-03-21 · demo
  31. AMonkeyAITools animated content directory@monkeyaitools promo for their curated AI-tools site, this time focused on animation/video generation tools. Link in bio.@monkeyaitools · 2024-02-26 · tool
  32. AMidjourney architectural sketch-in-context technique@design.input experimenting with Midjourney 'sketch in context' to fill in city facade lines on conceptual architectural sketches. Reference for arch/viz AI workflows.@design.input · 2023-08-11 · technique
  33. BPrompt engineering crash course — local models, system prompts, context engineeringA rapid-fire primer: run a 7–14B model quantized to 4 bits locally (e.g. on a 16 GB Orange Pi), set a system prompt that bans sycophancy and demands citations, add tool…@lizthedeveloper · 2025-09-21 · skill
  34. BGPT-5 Prompt Anatomy — OpenAI's six-part role-to-stop-condition templateA worked example of OpenAI's GPT-5 prompting structure: Role, Task, Context, Reasoning, Output format and Stop conditions, shown on a 'find three under-the-radar hikes…@theaifield · 2025-08-13 · technique
  35. BJSON image-prompt profiles — parameterized context for ChatGPT@chase.variantai demos using structured JSON 'context profiles' to drive image generation in ChatGPT, with dynamically swappable parameters. Proof-of-concept technique…@chase.variantai · 2025-07-09 · technique
  36. BUnreal Engine for cinematic artists — @badxstudio course teaser@badxstudio pitches their Ultimate Unreal Engine Course: real-time camera control, scrubbing animations while rehearsing shots, photoreal cinematic worlds. Comment…@badxstudio · 2025-07-07 · inspiration
  37. Bn8n + Veo 3 — Telegram-triggered AI vlog that auto-posts to YouTubeAn n8n automation where a Telegram message ('Bigfoot builds a log cabin vlog') becomes an eight-part story, each part rendered with Google Veo 3, stitched together and…@koen.agi · 2025-07-07 · demo
  38. BGemini 2.5 Pro — one-prompt interactive particle visualizer in a single HTML filePrompt Gemini 2.5 Pro to 'create a particle cloud visualizer that can change shape, color and other properties, interactive, in a single HTML file', answer its…@koen.agi · 2025-05-13 · technique
  39. BPrompt-Genie — auto-optimize ChatGPT prompts@promptgeniehq pitches prompt-genie.com, which rewrites your prompts into structured, goal-driven instructions. Caption summarizes the 'instruction + context + refine'…@promptgeniehq · 2025-05-04 · tool
  40. BAI credit-repair automation — @legacybuilder700Pitches using AI to analyze credit reports, auto-generate dispute letters, and mail them. Also references @thematthewlesko $50K small-business grant. Link in bio.2025-04-22 · inspiration
  41. BAd Deconstruction with GPT-4o — reverse-engineer a winning ad, regenerate for your brandA three-step workflow: upload a competitor ad to ChatGPT, have it analyze psychology, imagery, typography, color and composition through Cialdini, Rory Sutherland and…@thesocialalpha_ · 2025-04-09 · technique
  42. BAI rotoscoping — mask yourself into your own animations@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…@iamfesq · 2025-03-17 · technique
  43. BBuild Wars recap — AI gets you 80%, designers finish the 20%@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…@itsdesignertom · 2025-03-05 · design
  44. BVibe-coded games era — voxel MMO in a day, Claude plays Pokemon@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…@itsdesignertom · 2025-02-28 · news
  45. B4D spacetime explainer — @abdullteff@abdullteff explains Einstein's fourth dimension as time curvature in spacetime, using the (x,y,z,t) coordinate framing. Educational physics, not AI.@abdullteff · 2025-01-30 · inspiration
  46. BMusic AI agent experiment — @robonuggetsShort 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…@aitoolhub.co · 2024-12-30 · demo
  47. B50-neuron MNIST net — visualized prediction mapping (Eric Vyacheslav)Visualization (credit Eric Vyacheslav) of a 2-layer, 50-neuron network predicting handwritten digits, showing live activation/prediction mapping. Nice teaching/visual…@beautiful.digits · 2024-12-20 · demo
  48. BImage-to-video AI realism check — @setupspawn@setupspawn discusses how image-to-video AI (upload picture, animate it) is advancing faster than expected and the deepfake implications. No specific tool named.@setupspawn · 2024-11-08 · inspiration
  49. BText-to-visual icon generator — @aigptinsights@aigptinsights short demo of an AI tool that turns text into graphic visuals/icons. Tool unnamed in caption.@aigptinsights · 2024-09-27 · tool
  50. BClaude 3.5 Sonnet — build an app in minutes (Shawn Kanungo demo)@ainewscentral reshare of @shawnkanungo's viral 'build an app in minutes with Claude 3.5' demo. Early Claude vibe-coding showcase.@ainewscentral · 2024-09-05 · demo
  51. BPathfinding algorithms explained — brute force vs flood fill@sanctity.ai reshare of a Veritasium clip explaining pathfinding (brute force, flood fill, backtracking) using a mouse-in-maze analogy. Teaching reference.@sanctity.ai · 2024-08-29 · technique
  52. BRunway Gen-3 — hands-on first test of public text-to-videoA quick paid-tier test of Runway Gen-3 Alpha right after public release: a hyper-real macro prompt (miniature horned puppies on a fingertip, then butterfly wings) took a…@benkaluza · 2024-07-04 · demo
  53. BBopIt.app — 72-hour Claude 3.5 Sonnet vibe-coded launch@sebastian_volkis built and shipped BopIt.app in 72 hours using Claude 3.5 Sonnet, pulling 42K views and hundreds of users in 12 hours. Early case study of solo…@sebastian_volkis · 2024-07-04 · tool
  54. BTensorBoard Embedding Projector — see what word vectors really associateUses the TensorBoard Embedding Projector to explore a word2vec model's neighborhoods: 'cold' pulls in Soviet and war, 'sexy' pulls in Groucho and wigs. A quick, visual…@rajistics · 2024-07-01 · demo
  55. B800+ AI tools list — @socialtypro DM-bait@socialtypro offers a list of 800+ AI tools via comment 'BOOM'. Credits @vaibhavv.ai. Subject: curated AI tools directory.@socialtypro · 2024-05-12 · tool
  56. CChatGPT Prompt Stack — 7 role and memory prompts fronting an AI-agency pitchSeven generic ChatGPT prompts (role architecture, brain upload, outcome simulator, feedback loop, step-gated chain, session checkpoints, three-way refiner) used as the…@kekoamac · August 22, · technique
  57. CGovernment Contract Brokering Prompts — ChatGPT playbook for subcontracting middlemenSix ChatGPT prompts for finding government contract platforms, decoding RFPs, writing proposals as a coordinator, sourcing subcontractors, a compliance checklist and a…@dailyprompter · 2025-04-10 · technique

Other collections: CreativeAI Saves, Vol. 8AI Saves, Vol. 7Art I LikeMusicAI Saves, Vol. 4AI Saves, Vol. 5AI Saves, Vol. 3AI Saves, Vol. 6Quant & TradingAI Saves, Vol. 2Stocks, Vol. 2Stocks, Vol. 3Creative, Vol. 4Art InspirationGame TheoryPrompts

Filter in the catalogEvery entryAll guides