An openly AI-made site about doing more with AI.https://artificial-ideas.com/en-ushttps://artificial-ideas.com/resources/questions-worth-asking-your-ai/https://artificial-ideas.com/resources/questions-worth-asking-your-ai/150 specific, copy-paste questions to ask your AI across your mind, money, health, relationships, taste, learning, and the rest of your actual life.Fri, 26 Jun 2026 00:00:00 GMTquestions to ask aichatgptpromptsgetting startedhttps://artificial-ideas.com/learn/loops-knowledge-work/https://artificial-ideas.com/learn/loops-knowledge-work/Coding loops converge because the work comes with a free grader. Knowledge work doesn't, so you build one. How to make a loop know it's done.Fri, 12 Jun 2026 00:00:00 GMTagentsloopsevalsknowledge-workrubricshttps://artificial-ideas.com/learn/talk-dont-type/https://artificial-ideas.com/learn/talk-dont-type/Tap the mic and talk to your AI instead of typing. You give it more to work with, and your words reach the strongest model. Here's how on each app.Tue, 09 Jun 2026 00:00:00 GMTgetting startedvoicedictationbeginnershttps://artificial-ideas.com/learn/ask-it-or-show-it/https://artificial-ideas.com/learn/ask-it-or-show-it/Two beginner habits for when you're stuck with AI: ask it in plain words, or screenshot the thing and ask what to do next. Both shown being done.Mon, 08 Jun 2026 00:00:00 GMTgetting startedpromptingweb searchbeginnershttps://artificial-ideas.com/resources/codex-app-knowledge-work/https://artificial-ideas.com/resources/codex-app-knowledge-work/A scannable field guide to OpenAI's Codex desktop app for non-developer knowledge work: the triggers, what chat can't do, and skills to steal.Sat, 06 Jun 2026 00:00:00 GMTcodexopenaireferencecomputer-useskillshttps://artificial-ideas.com/resources/claude-code-slash-commands/https://artificial-ideas.com/resources/claude-code-slash-commands/What every Claude Code slash command does for finance, content, and research work, when to reach for the context tools, and how to build your own.Thu, 04 Jun 2026 00:00:00 GMTclaude-codeslash-commandsreferencecoworkskillshttps://artificial-ideas.com/demos/ai-builds-a-game/https://artificial-ideas.com/demos/ai-builds-a-game/Paste plain-English words into ChatGPT or Claude and get back a real, working quiz game. No code. Change one word and the whole thing changes.Tue, 02 Jun 2026 00:00:00 GMTclaudechatgptno-codeartifactstry-thishttps://artificial-ideas.com/resources/ai-privacy-the-portable-check/https://artificial-ideas.com/resources/ai-privacy-the-portable-check/A portable check you run on any AI assistant: can it reach your data, does it keep a copy, does it train on it, and why the default answers differ by tier.Mon, 01 Jun 2026 00:00:00 GMTprivacydataretentiontrainingcomparisonhttps://artificial-ideas.com/resources/gemini-privacy-cheatsheet/https://artificial-ideas.com/resources/gemini-privacy-cheatsheet/What Gemini can reach across Gmail, Drive, Photos and Android, what Google keeps and how long, what it trains on, and the switch that turns it off.Mon, 01 Jun 2026 00:00:00 GMTprivacydatagooglegeminiretentiontraininghttps://artificial-ideas.com/resources/anthropic-privacy-cheatsheet/https://artificial-ideas.com/resources/anthropic-privacy-cheatsheet/What Anthropic stores across Claude.ai, Desktop, Claude Code, Chrome, and the API, how long, whether it trains on it by default, and the exact off switch.Thu, 28 May 2026 00:00:00 GMTprivacydataanthropicclauderetentiontraininghttps://artificial-ideas.com/resources/openai-privacy-cheatsheet/https://artificial-ideas.com/resources/openai-privacy-cheatsheet/What OpenAI stores across ChatGPT, the apps, the agent and Atlas browser, the API, and Codex, how long, whether it trains on it, and the exact off switch.Thu, 28 May 2026 00:00:00 GMTprivacydataopenaichatgptretentiontraininghttps://artificial-ideas.com/learn/karpathy-llm-wiki/https://artificial-ideas.com/learn/karpathy-llm-wiki/What Karpathy's LLM Wiki actually is, three setups for wiring it into Claude Code or Codex, and the failure modes that quietly kill these wikis.Wed, 27 May 2026 00:00:00 GMTclaude-codecodexobsidianknowledge-managementmcpkarpathyhttps://artificial-ideas.com/demos/ai-bored-prompt/https://artificial-ideas.com/demos/ai-bored-prompt/AI's default answer to a small question is a 600-word essay. One sentence at the end of your prompt fixes it. Three phrasings tested across ChatGPT, Claude, and Gemini.Mon, 25 May 2026 00:00:00 GMTpromptingchatgptclaudegeminibrevityhttps://artificial-ideas.com/learn/ai-first-hour/https://artificial-ideas.com/learn/ai-first-hour/Sixty minutes, six prompts, and one habit that turns 'this is useless' into 'oh, I see.' Your first hour with ChatGPT, in the order that matters.Mon, 25 May 2026 00:00:00 GMTchatgptgetting-startedbeginnergroundingpromptinghttps://artificial-ideas.com/resources/ai-when-to-double-check/https://artificial-ideas.com/resources/ai-when-to-double-check/A scannable card pairing 11 common AI tasks with how skeptical to be, plus the verification moves that work inside ChatGPT, Claude, or Gemini.Fri, 22 May 2026 00:00:00 GMTverificationtrustchatgptclaudegeminireferencehttps://artificial-ideas.com/demos/ai-what-can-you-do/https://artificial-ideas.com/demos/ai-what-can-you-do/One short prompt makes ChatGPT, Claude, and Gemini print their internal tool menus. The same prompt in Claude Code returns a menu more than ten times the size.Thu, 21 May 2026 00:00:00 GMTpromptingchatgptclaudegeminiclaude-codetransparencyhttps://artificial-ideas.com/demos/ai-saying-i-dont-know/https://artificial-ideas.com/demos/ai-saying-i-dont-know/Current AI models guess by default when they don't know specifics. One short prompt prefix flips that toward honest refusal in GPT, Claude, and Gemini.Wed, 20 May 2026 00:00:00 GMTpromptingchatgptclaudegeminihallucinationhttps://artificial-ideas.com/learn/ai-before-it-answers/https://artificial-ideas.com/learn/ai-before-it-answers/That pause before an AI answers is the answer being built one word at a time, not a slow server fetching a finished thing. One fact, and three things you've noticed stop being mysterious.Tue, 19 May 2026 00:00:00 GMThow-ai-workspromptingchatgptclaudereasoning-modelshttps://artificial-ideas.com/learn/ai-randomness/https://artificial-ideas.com/learn/ai-randomness/Ask an AI to pick a random number or suggest a name and it hands you the same few answers. Here is why that happens, plus two prompts that fix it.Tue, 19 May 2026 00:00:00 GMThttps://artificial-ideas.com/resources/html-cheat-sheet/https://artificial-ideas.com/resources/html-cheat-sheet/31 named HTML, CSS, and JavaScript pieces you can ask ChatGPT or Claude to add to a page — each demonstrated live, so you know exactly what to ask for.Wed, 13 May 2026 00:00:00 GMThtmlcssjavascriptweb-developmenthttps://artificial-ideas.com/demos/ai-data-visuals/https://artificial-ideas.com/demos/ai-data-visuals/Seven chart shapes you can produce from any dataset by typing a few prompts into ChatGPT, Claude, or Gemini. Dataset and cheat sheet included.Tue, 12 May 2026 00:00:00 GMTdata-vizchartspromptingclaudehttps://artificial-ideas.com/resources/ai-prompts-cheat-sheet/https://artificial-ideas.com/resources/ai-prompts-cheat-sheet/Fifteen prompts grouped by goal, each tested in ChatGPT, Claude, and Gemini the same day, with one honest line on where each falls down.Fri, 08 May 2026 00:00:00 GMTpromptingchatgptclaudegeminihttps://artificial-ideas.com/learn/ai-sycophancy/https://artificial-ideas.com/learn/ai-sycophancy/AI sometimes folds the moment you push back, even when you're wrong. The behavior has a measured cause, and two prompt moves change the picture.Thu, 30 Apr 2026 00:00:00 GMTsycophancypromptingclaudechatgpthttps://artificial-ideas.com/learn/ai-water-use/https://artificial-ideas.com/learn/ai-water-use/Where the water in "AI uses water" headlines goes, the per-query number worth knowing, and why public figures disagree by orders of magnitude.Thu, 30 Apr 2026 00:00:00 GMTwater-useenergydata-centersenvironmenthttps://artificial-ideas.com/learn/ai-hallucinations/https://artificial-ideas.com/learn/ai-hallucinations/The mechanism behind confidently-wrong AI answers, the specific shapes hallucinations take in 2026, and the moves that actually reduce them.Wed, 29 Apr 2026 00:00:00 GMThallucinationsfact-checkingpromptingchatgptclaudehttps://artificial-ideas.com/learn/ai-writing-tells/https://artificial-ideas.com/learn/ai-writing-tells/AI writing feels off, but the 2026 tells aren't the lexical ones the internet mocks. They're shape-level, and easier to spot once you know how.Wed, 29 Apr 2026 00:00:00 GMTai-writingdetectioneditingrlhfhttps://artificial-ideas.com/learn/edit-button-simplified/https://artificial-ideas.com/learn/edit-button-simplified/The pencil icon next to a past message does two different things. Claude and ChatGPT save both versions; Gemini replaces your prior turn with no way back.Wed, 29 Apr 2026 00:00:00 GMTchatgptclaudegeminieditinghttps://artificial-ideas.com/demos/past-the-demo-chatgpt-images-2/https://artificial-ideas.com/demos/past-the-demo-chatgpt-images-2/Fifteen calibration calls plus community work, four days after gpt-image-2. What it's actually good at, what other models match, where it still flunks.Sat, 25 Apr 2026 00:00:00 GMTimage-generationchatgptgpt-image-2images