August 3, 2025

This week, I learned: From A.I. Is About to Solve Loneliness. That’s a Problem: “Blindly stifling every flicker of boredom with enjoyable but empty distractions precludes deeper engagement with the messages boredom sends us about meaning, values, and goals.” Maybe the best thing about boredom is what it forces us to do next. Here’s when be candid vs polite. #beliefs ChatGPT If there’s high trust (i.e. the other person trusts you): Important topic/decision: Be candid Unimportant: Follow culture (e.g. in Japan, you’d be polite; in The Netherlands, you’d be candid) Low trust: Important: Earn trust first Unimportant: Be polite I didn’t realize that it was Luis Alvarez (whom I know from his work on the bubble chamber) is the same person who figured out that an asteroid killed dinosaurs. He also used muon tomography to search pyramids for hidden chambers and figured out Kennedy was shot from behind. Added his biography, Collisions to my to-read list. Ref Benjamin Green suggests that OpenAI Study mode is sycophantic. E.g. in this conversation, ChatGPT carefully balances truth and politeness. A reader might misinterpret that as agreement. But sometimes, we need candor. Politeness trades clarity for harmony. People who trust AI should tell it to be more candid. ⭐ Here’s my current response when asked, “How should I use LLMs better”: Use the best models, consciously. O3 (via $20 ChatGPT), Gemini 2.5 Pro (free on Gemini app), or Claude 4 Opus (via $20 Claude). The older models are the default and far worse. Speak & listen, don’t just type & read. I had to resist the temptation to ignore ChatGPT response when a colleague read it out. We are patient with and have respect for humans but not for AI. The value we derive requires both. Suggestion: Speak and listen rather than type and read. It’s hard to skip and easier to stay in the present. It’s also easier to ramble than type. Keep an impossibility list. There is a jagged edge that moves. When you note down what’s impossibile today and retry every month, you can see how that edge shifts. Wait for better models. Many problems can be solved just by waiting a few months for a new model. You don’t need to find or build your own app. Make context easily available. Context is one of the biggest enablers for LLMs. Use search, copy-pasteable files, previous chats, connectors, APIs/tools, or any other way to give LLMs examples and context. Have LLMs write code. LLMs are bad at math. They’re good at languages, including code. Running the code gives output with low hallucinations. This combination can solve a WIDE variety of problems that need creativity and reliability. Learn AI coding. 1. Build a game with ChatGPT/Claude/Gemini. 2. Improve it. 3. Create a tool useful to you. 4. Publish it on GitHub. APIs are cheaper than self hosting. Avoid self-hosting. Datasets are more important than fine-tuning. You can always fine-tune a newer model as long as you have the datasets. Most CDNs use package.json "exports" for the default URL of npm packages. jsDelivr uses jsDelivr > browser > main (does not use exports - a notable exception) unpkg.com uses exports.default > browser > main skypack.dev uses exports.default > module > main esm.sh uses esm.sh.bundle > exports.default jspm.dev uses jspm > exports.default > main A quick way to transcribe audio recordings is via: llm --system "Transcribe" --attachment recording.mp3 --model gemini-2.5-flash "This recording is about (context)". Providing context improves transcription, e.g. by spelling names and technical terms correctly. Since Gemini has a 1M input context, using Gemini CLI as a sub-agent from Claude Code using the -p or --prompt flag lets it crunch large code bases and pass relevant responses back to Claude Code. #ai-coding While ChatGPT Codex aligns with my minimalistic style and follows instructions very well, it also tends to remove comments in my code and oversimplifies. Jules is better than that regard. #ai-coding Teaching vibe coding is satisfying, too. I guided a developer to write a Python workflow by providing 2 prompts. Both of these were one-shotted by Claude 4 Sonnet. The entire process took 20 min with me guiding them over the phone. #ai-coding “Write a Python script to extract a page from a PDF file and save it.” Followed by “Write minimal code. Drop error handling.” “Write a Python script to pass a PDF file to an LLM for OCR and print the result. Use this code sample… [PASTED CODE].” Followed by “Write minimal code. Drop error handling.” LLM users are maturing quickly. Early adopters who are open to understand the generic capabilities of LLMs through demos are somewhat saturated. The early majority have come in. They aren’t interested in generic capabilities. They’re looking for solutions that solve their specific problem. Soon the late majority will come in asking for existing solutions that have already solved their problem for many others. How can a generic industry-agnostic technology team create demos or solutions for this early majority when we don’t yet know their use cases? ChatGPT Maintain a living “pain wiki” that teams updates daily. Create thin-slice demos that solve ONE pain-point. Re-configure with an industry skin. Result: ten demos that feel bespoke. Publish ROI, client list. Run as one-day POCs with client data. Open toolkit to partners. Track popularity of tools. Archive unused ones. Consolidate popular ones into solutions. AI closes the gap between junior & senior devs – even when both use AI. Quality doesn’t suffer much. So onboarding can be faster, compensation ladder may shorten. When using AI, developers code more and “project manage” less. Collaboration need reduces and hierarchies are likely to flatten. Generative AI and the Nature of Work #ai-coding FFmpeg in plain english lets you run ffmpeg in the browser with plain English commands. It converts the task using an LLM into an ffmpeg command, runs it in browser via WASM (without uploading the file) and saves the output locally. This is very useful, since ffmpeg has one of the most complex command line options. I use an llm template defined via: llm --save ffmpeg --model gpt-4.1-mini --extract --system 'Write an ffmpeg command' which I can use like this: llm -t ffmpeg 'Crossfade a.mkv (1:00-1:30) with b.mkv (2:10-2:20), 3s duration' OpenAI’s prompt engineering guide recommends an interesting tactic that includes this prompt snippet, which I think is very powerful. ask clarifying questions when needed ...