~/adi

Running a local coding agent with LM Studio and OpenCode

I’ve been a huge fan of Claude Code since it launched. Over the past few months, I’ve been using it extensively across all kinds of projects. Claude Code is still the best tool out there, though others (Gemini CLI) are catching up. I recently discovered OpenCode, an open-source model agnostic framework that supports local models, and used it to test gpt-oss-20b, qwen3-coder-30b — currently the best open source coding models with tool calling. [5 min →]

My mobile claude code setup

I previously wrote about using Claude Code from my phone.
Since then, I’ve ported that to a headless Mac Mini. This is the updated setup. [6 min →]

Tools of leverage not reliance

Quoting David Kenji Chang on AI assistance:

We need to use these tools as tools of leverage, not tools of reliance

The weird intern in your terminal

I gave a talk at Tokyo AI #10 exploring how you can make Claude Code and other AI tools into coworkers. Below are the slides and my presenter notes augmented with a transcript from memory. References are at the end. [9 min →]

Why I Deleted My Second Brain: A Journey Back to Real Thinking

I feel really seen by this. For years I’ve tried to be dilligent with PKM and read-it-later tools. There are some workflows that are useful e.g. these quotes are parsed from my highlights of the transcript of the Youtube video in Reader, but overall my journey mirrors the author’s, and the underlying psychology it exposes is uncomfortable to comprehend. I’m not sure I’ll delete it all, but it’s given serious pause for thought.

over time, my second brain became a moraleum, a dusty collection of old selves, old interests, old compulsions piled on top of each other like geological strata. Instead of accelerating my thinking, it began to replace it. Instead of aiding memory, it froze my curiosity into static categories. [4 min →]

TIL: Webkit supports videos in <img> tags

I just published a post with gifs and videos and was pretty happy with how it was looking. A few minutes later, a friend messaged me: [2 min →]

My Claude Code setup

This is a list of the various things I’ve done to my claude code setup. A lot of it is not well documented, so I’m pulling it together as a master list here. [2 min →]

Teaching Claude to Commit Like a Human

Claude Code is my weird-intern-in-a-terminal¹ and it’s surprisingly useful for all kinds of things beyond writing code. For example, reviewing and commiting the code it just wrote. [6 min →]

Claude Code Tips for SWE

I’ve been been using Claude Code a lot the past 2 weeks, enough that I hit the Max plan rate limits 3-4x daily. These tips have been the biggest quality of life improvement for me. You can find more in Anthropic’s best practices. [2 min →]

Remote controlling Claude Code

Claude Code amazed me at launch. [4 min →]

The Japanese Immigration test for AGI

There’s no widely agreed-upon definition of AGI, and everything with LLMs is vibes dominated anyway, so the best we have is “I’ll know when I see it”. [2 min →]

Remarks on AI From NZ

Quoting Neal Stephenson:

Maybe a useful way to think about what it would be like to coexist in a world that includes intelligences that aren’t human is to consider the fact that we’ve been doing exactly that for long as we’ve existed, because we live among animals. Animals have intelligences of many different kinds. We’re used to thinking of them as being less intelligent than we are, and that’s usually not wrong, but it might be better to think of them as having different sorts of intelligence, because they’ve evolved to do different things. [7 min →]

The purpose of software should be to minimize the friction between intent and result

Quoting tautologer:

the optimal user interface is that you simply say this sentence aloud and then the list appears on your screen all the going to websites and clicking and filtering and so on is fundamentally cruft [1 min →]

Get That Job at Google

Quoting Steve Yegge:

First, you can’t tell interviewers what’s important. Not at any company. Not unless they’re specifically asking you for advice. You have a very narrow window of perhaps one year after an engineer graduates from college to inculcate them in the art of interviewing, after which the window closes and they believe they are a "good interviewer" and they don’t need to change their questions, their question styles, their interviewing style, or their feedback style, ever again. [1 min →]

Not Nearly Enough People Are Talking About the Implications Of Klarna rolling back some of their AI bets.

Quoting Chamath Palihapitiya:

Replacing determinism or humans with probabilistic code is fraught with edge cases and require new ways of software development and process engineering that aren’t well solved yet. [1 min →]