#code-agents #prompt-engineering #beliefs#best-practices #beliefs#markdown/sdcard/btsnoop_hci.log (Wireshark).getAllCellInfo()), with appropriate telephony permissions.adb shell dumpsys netstats.dumpsys batterystats.#automation#future#image-generation #llm-ops #markdown#ai-coding #code-agents#ai-coding #best-practices #code-agents #github #markdown #prompt-engineering #write#ai-coding #code-agents #dev #github #markdowngh CLI to fetch line-wise comments from a PR and make requested changes (e.g. renaming, refactoring, adding types, etc.)#best-practices #darker-color#ai-coding #github #markdown#chatgpt#future #gpu#automation #best-practices #future #gpu #optimization #prompt-engineering<link rel="alternate" type="text/markdown" title="LLM-friendly version" href="/llms.txt"> is an emerging approach for pointing to LLMs.txt. It works. I asked Codex to read the CloudFlare vitest page. It read the file truncating the middle, found the <link rel="alternate" type="text/markdown" href="https://developers.cloudflare.com/workers/testing/vitest-integration/write-your-first-test/index.md"/ link in it, and reasoned "Considering fetching markdown instructions" and fetched the Markdown page. Giles' Blog #html #llm-ops #markdown#markdown#ai-coding #code-agents #embeddings #future #github"security.auth.selectedType": "gemini-api-key" in ~/.gemini/settings.jsonexport GOOGLE_GEMINI_BASE_URL=https://llmfoundry.straive.com/gemini/ (or your AI router base URL for Gemini)export GEMINI_API_KEY=... (your AI router API key)#future #llm-ops #prompt-engineering#code-agents!, e.g. !ls -la or even !bash. It's added to the chat.GEMINI_SYSTEM_MD=... gemini -p "task" --yolo --format json < input.txt to run Gemini with a different system prompt and feed it input.txt to run in a pipeline. (FYI: Codex does not send a default system prompt, so there's nothing to override.)/memory add feature helps with this.gemini --checkpointing is a useful "undo" feature. /restore rolls you back to a specific checkpoint. The overhead is small.#speech-to-text #tts #voice-cloning#pricingcurl "https://api.openai.com/v1/organization/costs?start_time=$TIMESTAMP&project_ids=$PROJECT_ID&group_by=line_item"curl "https://api.openai.com/v1/organization/usage/audio_speeches?start_time=$TIMESTAMP&project_ids=$PROJECT_ID&group_by=model"