Joel Martin
@kanaka.bsky.social
Creator of mal/make-a-lisp, noVNC, websockify, clj-protocol, conlink, instacheck, miniMAL, wam, wac, warpy, raft.js (github.com/kanaka).
Interested in Clojure, WebAssembly/wasm, AI/LLMs, JS, Rust, network protocols, web browsers, testing, etc.
Interested in Clojure, WebAssembly/wasm, AI/LLMs, JS, Rust, network protocols, web browsers, testing, etc.
And yes, the "large real-world value" is that I personally want this to work well right now.
December 1, 2025 at 7:26 PM
And yes, the "large real-world value" is that I personally want this to work well right now.
And to be clear, mal is in the training data and has been since the beginning (there are tells), and mal has almost 1000 tests. But it is still a notable milestone for me. And I have some private evals that also show a big jump in capability and code quality in the latest models.
November 26, 2025 at 4:14 PM
And to be clear, mal is in the training data and has been since the beginning (there are tells), and mal has almost 1000 tests. But it is still a notable milestone for me. And I have some private evals that also show a big jump in capability and code quality in the latest models.
Sonnet 4.5 (in opencode) was a major step change for my unofficial eval: complete an implementation of a mal interpreter (all 11 steps), without any intervention. Previous models/agents couldn't get past the second step without help. This is a task that takes me 6-16 hours by hand (from scratch).
November 26, 2025 at 4:08 PM
Sonnet 4.5 (in opencode) was a major step change for my unofficial eval: complete an implementation of a mal interpreter (all 11 steps), without any intervention. Previous models/agents couldn't get past the second step without help. This is a task that takes me 6-16 hours by hand (from scratch).
Reposted by Joel Martin
Prototypes are the most powerfully tool I know of for increasing the productivity of conversations about what software should do and how it should work
They're tools for thinking
They're tools for thinking
September 21, 2025 at 8:37 PM
Prototypes are the most powerfully tool I know of for increasing the productivity of conversations about what software should do and how it should work
They're tools for thinking
They're tools for thinking
Book added to my reading queue! BTW, if it's interesting I have a couple of posts on building really simple coding agents:
* LiteLLM based: kanaka.github.io/blog/litellm...
* llm library based: kanaka.github.io/blog/llm-age...
Code is MIT so feel to use, adapt, or reference it for concrete examples.
* LiteLLM based: kanaka.github.io/blog/litellm...
* llm library based: kanaka.github.io/blog/llm-age...
Code is MIT so feel to use, adapt, or reference it for concrete examples.
An LLM Coding Agent in 6 incremental steps and about 140 lines of python
I will show you how to create a working LLM coding agent in 6 incremental steps (and about 140 lines of code). We will use the python LiteLLM library and use Github Copilot which means all you need is...
kanaka.github.io
June 16, 2025 at 6:45 PM
Book added to my reading queue! BTW, if it's interesting I have a couple of posts on building really simple coding agents:
* LiteLLM based: kanaka.github.io/blog/litellm...
* llm library based: kanaka.github.io/blog/llm-age...
Code is MIT so feel to use, adapt, or reference it for concrete examples.
* LiteLLM based: kanaka.github.io/blog/litellm...
* llm library based: kanaka.github.io/blog/llm-age...
Code is MIT so feel to use, adapt, or reference it for concrete examples.
Weird, I don't know why the embedded link card is broken. The full link in the post works though.
June 13, 2025 at 1:02 AM
Weird, I don't know why the embedded link card is broken. The full link in the post works though.
I can recognize good writing but can't generate it easily. I can arrive at decent prose, but the phase from unstructured thoughts until first draft is 90% of the effort/time. I think I'm not alone.
Me: write notes
LLM: first draft
Me+LLM: update until well-written, well-structured, and in my voice.
Me: write notes
LLM: first draft
Me+LLM: update until well-written, well-structured, and in my voice.
May 8, 2025 at 6:10 PM
I can recognize good writing but can't generate it easily. I can arrive at decent prose, but the phase from unstructured thoughts until first draft is 90% of the effort/time. I think I'm not alone.
Me: write notes
LLM: first draft
Me+LLM: update until well-written, well-structured, and in my voice.
Me: write notes
LLM: first draft
Me+LLM: update until well-written, well-structured, and in my voice.
Reposted by Joel Martin
Completely agree - code is such an interesting application because you get a basic form of "fact checking" for free, unlike with prose simonwillison.net/2025/Mar/2/h...
Hallucinations in code are the least dangerous form of LLM mistakes
A surprisingly common complaint I see from developers who have tried using LLMs for code is that they encountered a hallucination—usually the LLM inventing a method or even a full …
simonwillison.net
May 8, 2025 at 4:41 PM
Completely agree - code is such an interesting application because you get a basic form of "fact checking" for free, unlike with prose simonwillison.net/2025/Mar/2/h...
Reposted by Joel Martin
I think the one counterexample is that it's good at writing a lot of code, which is creating more text. My rough rule of thumb is that LLMs are good when it's easy to verify the output as correct, which is quite a lot of things
May 8, 2025 at 4:30 PM
I think the one counterexample is that it's good at writing a lot of code, which is creating more text. My rough rule of thumb is that LLMs are good when it's easy to verify the output as correct, which is quite a lot of things
I do a similar thing to determine which mal implementations to run tests for (parallel matrix strategy) depending on what files have changed: github.com/kanaka/mal/b... I could probably simplify my python filter script using that dorny action.
github.com
May 4, 2025 at 11:12 PM
I do a similar thing to determine which mal implementations to run tests for (parallel matrix strategy) depending on what files have changed: github.com/kanaka/mal/b... I could probably simplify my python filter script using that dorny action.