Tracked topic
…I supplied my landing page document to Sonnet 4.6 (Adaptive), GPT -4o (with Canvas), and Gemini 2.5 Pro (with Canvas). I gave identical prompts to each of them, and intentionally…
…My first model was gpt-oss 20B, which I got going on the 8GB GPU through some offloading to system RAM. Since then I've moved to smaller, more optimized models that…
…These aren't tasks that need GPT-5.4 or Claude Opus 4.7 . They just need a model that's good enough to be helpful, and Gemma 4 clears that bar…
…I don’t always know ahead of time whether I need Claude, Gemini, DeepSeek, Mistral, GPT, or something smaller and cheaper. Sometimes I need a model that writes cleanly, sometimes I need…
…to find what the tool said two days ago, the frustration starts to build up. GPT-5.5, Opus 4.8, or Gemini 3.5 may be more advanced than ever, and…
…Then I tried my first local LLM, which was gpt-oss 20B, and the PC basically tapped out on the spot. I didn't know much about local AI back then so…
…For local, I’m going with my tried-and-true gpt-oss20b model . I honestly didn’t change my system prompt or any of my other settings in either one, because that…
…Being able to point Open Notebook at Claude, GPT, or whatever's best for the task is a huge perk. Open Notebook is great, but I'm not its target audience Notebook…
…I spent the next hour hooking it up to Blinko , Paperless-GPT (and AI), Karakeep , VS Code, Claude Code, Open WebUI, and other FOSS applications in my arsenal. I plan to test…
…Now, with newer models like GPT-5, it also has preview mode for code, so you can visually interact with whatever you built. Both Gemini and ChatGPT render React and HTML code…
