If you aren’t using Qwen3-Max-Thinking already, you’re … just like me. As much as I try to stay current, I also have to get real work done. So for me it’s the latest Claude Opus and the latest Gemini, for both writing and coding. I bounce between the two: most days I start with Opus, and when I hit rate limits on my plan, I switch to Gemini.
Chat windows are still weirdly clumsy. The next step up is letting a chatbot drive your browser. It’s not exactly enterprise-safe, and I’m more comfortable with Claude’s Chrome extension than with the OpenAI or Perplexity browsers.
Then there are command-line clients like Claude Code or Gemini CLI. You can tell them to search through your stuff, patch a codebase, or spin up something new. You say what you want, it figures out the steps (sometimes) on its own.
For people who don’t want to live in a terminal, Anthropic has launched Claude Cowork. It runs in the Claude desktop app and feels like a more user-friendly interface for the same concepts as Claude Code: you make a request, Claude makes a plan, then executes it—breaking the work into smaller tasks, testing, and iterating along the way.
I gave it access to a copy of my website’s innards, WordPress theme files, 460 in total, and asked how to make a small design tweak. It told me exactly which file and which line to change. Not the sophisticated agent orchestration with pre-defined rules quite yet. But it is a start.
Two good intros for journalists/writers:
– Florent Daudens on Claude Code
– Casey Newton in his newsletter Platformer
But now that I’ve mentioned Qwen, let’s at least fire a few prompts, shall we?
Chatbots often stumble on simple questions, and Qwen3-Max is no exception. When asked about the current best chatbots for journalistic work, it spits out year-old model names, even though it does a web search. When pressed, it eventually gets to Opus 4 and Gemini 2. Still out of date.
DeepSeek does better, but only if you explicitly enable web search. I had to think of my colleague Alba Mora Roca, who warns about the Western bias of chatbots.
So I asked in Chinese for the three leading voices in AI and journalism:
– Qwen3-Max searches the web and finds two Americans and one Chinese scholar, 喻国明. Interesting!
– DeepSeek doesn’t search the web. Result: two Americans, one Frenchman.
– GPT 5.2 with web search names its own company boss Sam Altman first, along with an Indian and a British journalist.
– Mistral’s LeChat is the only one to name three scientists, from Taiwan, Britain, and China.
Anecdotal as this is, I’m sure there are at least three lessons in here you could come up with.
Even without the help of AI.
