Dakota Chambers


AI Usage

It’s important to set personal limits on how we approach and use AI tools as they becomes more prevalent throughout our society. I have created this permanent page, inspired by Derek Sivers and Damola Morenikeji. I will keep it updated with how I personally use AI to add value to my life in a sustainable way.

Subscriptons

I currently subcribe to OpenCode Go, ChatGPT Plus, and Gemini.

  • OpenCode Go is a low cost subscription that gives me access to workhorse open models for coding like DeepSeek.
  • ChatGPT Plus gets me access to GPT Sol when I need a more powerful model for planning or complex tasks, and it offers essentially unlimited usage of Luna, OpenAI’s low cost model. Luna on max effort is a really good “workhorse” model, similar to DeepSeek Flash.
  • I primarily subscribe to Gemini for other Google features, but I do use the app for quite a bit of Q&A and research. Gemini has excellent multi-modal capabilities and text-to-speech synthesis that make a joy to use.

I also keep a small balance in my personal OpenRouter account which allows me to experiment with different models and test new features.a

Writing

I almost never use AI to help me write. Writing is challenging, but the challenge is what makes it worth it. Think of writing like exercise for the brain. Your brain, like other parts of your body, needs exercise to stay healthy. I enjoy flexing those writing muscles - and you should too!

And I write quite a bit. The nature of working in a mostly-remote company means that a lot of our work is done asynchronously via written communication. I can see how it’s tempting to use AI to help you write, but I think it’s overall more harmful than helpful. Formulating thoughts to the point you can write them down and communicate them clearly is an incredibly valuable process and clearly elevates the quality of your work. Writing well makes you really think about what you want to say and forces you to string together sometimes disjointed thoughts into something concrete.

Research

I use AI (ChatGPT, Gemini, or Kagi Quick Answer) for general Q&A and research. This is an area modern LLMs excel at. Combine that with web search and multi-modal capabilities, these tools are, quite frankly, incredible.

You do need to be cautious when using AI tools for research. After all LLMs cannot actually reason and simply use mathematical probability to generate one token at a time. LLMs are notorious for “hallucinating” facts precisely because of this. LLMs with better training data will be better at reproducing accurate information, but the generated text can only be as accurate as the training data. And guess what? There’s a lot of inaccurate information out there on the internet.

I like to treat text generated by LLMs like I do other untrusted information on the internet. Trust but verify. Use it as a jumping-off point for future, more in-depth research. I wouldn’t use it to answer a question that I need to 100% verify is correct, but I think it can be an incredibly useful tool to help generate ideas.

Software Development

Agents

I’m all-in on agents for software development and related work.

The agentic coding take-off that started in December of 2025 is very real. Claude Code, Codex, OpenCode, Pi, etc are just incredible tools. I began using these at the start of 2026 and now the day-to-day work of a software engineer is mostly interacting with LLMs via these coding harnesses. I am no exception.

CLIs

CLIs are making a major comeback in 2026 because it turns out they’re the perfect interface for generic agents to interact with your application/service data. If you have a powerful API (and a good CLI that exposes it) an agent can do pretty much anything.

Everything Else

  • I like typing. I have a great keyboard and I’m pretty fast, but I have started experimenting with dictation software.
    • I am the Handy app on MacOS and Linux which uses local models for voice-to-text transcriptions.