{"data":{"slug":"swyxio-ai-notes","name":"ai-notes","tagline":"Notes for software engineers on recent AI developments","github_url":"https://github.com/swyxio/ai-notes","owner":"swyxio","repo":"ai-notes","owner_avatar_url":"https://avatars.githubusercontent.com/u/6764957?v=4","primary_language":"HTML","stars":6243,"forks":560,"topics":["ai","gpt","gpt-3","multimodal","openai","prompt-engineering","stable-diffusion"],"archived":false,"github_pushed_at":"2026-02-16T06:45:25+00:00","maintenance_label":"Slowing","url":"https://www.graphcanon.com/tools/swyxio-ai-notes","markdown_url":"https://www.graphcanon.com/tools/swyxio-ai-notes.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/swyxio-ai-notes","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=swyxio-ai-notes","description":"notes for software engineers getting up to speed on new AI developments. Serves as datastore for https://latent.space writing, and product brainstorming, but has cleaned up canonical references under the /Resources folder.","homepage_url":"https://latent.space/","license":"MIT","open_issues":9,"watchers":176,"ai_summary":"Provides an organized reference for AI advancements and serves as resource repository for Latent.Space content creation, focusing on GPT models and multimodal applications","readme_excerpt":"# AI Notes\n\nnotes on AI state of the art, with a focus on generative and large language models. These are the \"raw materials\" for the https://lspace.swyx.io/ newsletter.\n\n> This repo used to be called https://github.com/sw-yx/prompt-eng, but was renamed because [Prompt Engineering is Overhyped](https://twitter.com/swyx/status/1596184757682941953). This is now an [AI Engineering](https://www.latent.space/p/ai-engineer) notes repo.\n\nThis Readme is just the high level overview of the space; you should see the most updates in the OTHER markdown files in this repo:\n\n- `TEXT.md` - text generation, mostly with GPT-4\n\t- `TEXT_CHAT.md` - information on ChatGPT and competitors, as well as derivative products\n\t- `TEXT_SEARCH.md` - information on GPT-4 enabled semantic search and other info\n\t- `TEXT_PROMPTS.md` - a small [swipe file](https://www.swyx.io/swipe-files-strategy) of good GPT3 prompts\n- `INFRA.md` - raw notes on AI Infrastructure, Hardware and Scaling\n- `AUDIO.md` - tracking audio/music/voice transcription + generation\n- `CODE.md` - codegen models, like Copilot\n- `IMAGE_GEN.md` - the most developed file, with the heaviest emphasis notes on Stable Diffusion, and some on midjourney and dalle.\n\t- `IMAGE_PROMPTS.md` - a small [swipe file](https://www.swyx.io/swipe-files-strategy) of good image prompts\n- **Resources**: standing, cleaned up resources that are meant to be permalinked to\n- **stub notes** - very small/lightweight proto pages of future coverage areas\n\t\t  - `AGENTS.md` - tracking \"agentic AI\"\n- **blog ideas**- potential blog post ideas derived from these notes bc\n\n\n\n<details>\n<summary>Table of Contents</summary>\n\n- [Motivational Use Cases](#motivational-use-cases)\n- [Top AI Reads](#top-ai-reads)\n- [Communities](#communities)\n- [People](#people)\n- [Misc](#misc)\n- [Quotes, Reality & Demotivation](#quotes-reality--demotivation)\n- [Legal, Ethics, and Privacy](#legal-ethics-and-privacy)\n\n</details>\n\n\n## Motivational Use Cases\n\n- images\n  - https://mpost.io/best-100-stable-diffusion-prompts-the-most-beautiful-ai-text-to-image-prompts\n  - [3D MRI synthetic brain images](https://twitter.com/Warvito/status/1570691960792580096?) - [positive reception from neuroimaging statistician](https://twitter.com/danCMDstat/status/1572312699853312000?s=20&t=x-ouUbWA5n0-PxTGZcy2iA)\n  - [multiplayer stable diffusion](https://huggingface.co/spaces/huggingface-projects/stable-diffusion-multiplayer?roomid=room-0)\n- video\n  - img2img of famous movie scenes ([lalaland](https://twitter.com/TomLikesRobots/status/1565678995986911236))\n    - [img2img transforming actor](https://twitter.com/LighthiserScott/status/1567355079228887041?s=20&t=cBH4EGPC4r0Earm-mDbOKA) with ebsynth + koe_recast\n    - how ebsynth works https://twitter.com/TomLikesRobots/status/1612047103806545923?s=20\n  - virtual fashion ([karenxcheng](https://twitter.com/karenxcheng/status/1564626773001719813))\n  - [seamless tiling images](https://twitter.com/replicatehq/status/1568288903177859072?s=20&t=sRd3HRehPMcj1QfcOwDMKg)\n  - evolution of scenes ([xander](https://twitter.com/xsteenbrugge/status/1558508866463219712))\n  - outpainting https://twitter.com/orbamsterdam/status/1568200010747068417?s=21&t=rliacnWOIjJMiS37s8qCCw\n  - webUI img2img collaboration https://twitter.com/_akhaliq/status/1563582621757898752\n  - image to video with rotation https://twitter.com/TomLikesRobots/status/1571096804539912192\n  - \"prompt paint\" https://twitter.com/1littlecoder/status/1572573152974372864\n  - audio2video animation of your face https://twitter.com/siavashg/status/1597588865665363969\n  - physical toys to 3d model + animation https://twitter.com/sergeyglkn/status/1587430510988611584\n  - music videos \n    - [video killed the radio star](https://www.youtube.com/watch?v=WJaxFbdjm8c), [colab](https://colab.research.google.com/github/dmarx/video-killed-the-radio-star/blob/main/Video_Killed_The_Radio_Star_Defusion.ipynb) This uses OpenAI's Whisper speech-to-text, allowing you to take a YouTube video & create","github_created_at":"2022-09-04T07:13:19+00:00","created_at":"2026-07-11T11:57:02.867064+00:00","updated_at":"2026-07-28T00:00:40.246844+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"gpt","name":"gpt"},{"slug":"multimodal","name":"multimodal"},{"slug":"openai","name":"openai"},{"slug":"prompt-engineering","name":"prompt-engineering"},{"slug":"stable-diffusion","name":"stable-diffusion"}],"trust":{"provenance":{"is_fork":false,"github_id":532465933,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-28T00:00:39.529Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":161,"last_release_at":null},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:57:04.014Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-28T00:00:39.978Z"},"languages":{"value":["html"],"source":"github.language","observed_at":"2026-07-28T00:00:39.978Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-28T00:00:39.978Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":[],"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"requires_docker":false},"when_to_use":["You are working on projects involving GPT models or multimodal applications and require the latest insights from Latent.Space content creation efforts.","Your team is looking to enhance knowledge of GPT-3, prompt engineering, or stable-diffusion techniques specifically."],"when_not_to_use":["The focus of your project lies beyond GPT models or multimodal applications as ai-notes does not delve into non-GPT AI advancements.","You are in search of comprehensive tutorials on all major AI frameworks, since ai-notes is primarily centered around specific topics under Latent.Space."],"source":"enrich:decision_facts","observed_at":"2026-07-15T09:03:18.417Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":false},"decision_summary":[{"label":"Adopt for","value":"ai-notes offers curated resources centered around recent AI advancements for software engineers, particularly in GPT models and multimodal applications."},{"label":"License detail","value":"The MIT License grants permission to use the tool freely under certain conditions, typically including attribution and non-liability terms."}]}}