Yeah I need to try codex a bit more for code review, maybe use it with a GLM or Sonnet executor
06.03.2026 00:42
👍 0
🔁 0
💬 1
📌 0
Yeah I need to try codex a bit more for code review, maybe use it with a GLM or Sonnet executor
Detailed to a degree unlike other models, not comprehensive like every model
(Why I strongly believe in using cross model review at the task and phase level)
I apparently have Tesco Pitas down as well.
Made bagels today 🥯 🤤
# isn’t perfection (lesser models and Claude generate imperfect code under all sorts of constraints and prompting in my experience)
I’ve built my own set up for agentic coding using Claude but I would say it’s perfection; I’m constantly refining it.
If I just use a minimal harness and get Claude to build it, I need to refactor it anyway because it’s an unreliable mess
Soon to be MIT/Linux, because they’ll be vibe porting the GNU toolchain to Rust and it won’t be having a FSF-prescribed license
Mature companies I talk to have significant plans to move off any stack that isn’t otherwise JS/Python/Java/.NET (PHP or Ruby especially). Performance sensitive stuff goes to Rust, but only if necessary.
“The market” and AI have definitely converged the language and library space for new startups to Node.js and React in Australia. Everyone is scared to build outside of them because the talent pool here is so small and its hard enough to hire.
Discovered only through conversation at a meetup last night that a mutual friend was an Elixir developer in a previous life - apparently there was a small number of Elixir shops in Australia some time back.
In think it uses the lazy plugin manager under the hood, but gives you a structure for adding plugins one by one
If you’re initialising a neovim from scratch I highly recommend github.com/nvim-lua/kic...
Overproofing the sourdough nowadays. My starter is a mutant beast but it only like the good stuff
My slides (and my video, soon to be linked) from last night are here: www.chrisarmstrong.dev/posts/sydney...
My slides from last night (and soon the video) are linked here: www.chrisarmstrong.dev/posts/sydney...
I really do need to link to my coding guidelines though and somehow store them separately to the repository, including the dependent agent configuration
This was recorded too 🎥 so hopefully i can post a link
At least Kimi K2.5 is fast (albeit twice as costiy at m2.5, which is dirt cheap for a reason)
Experimenting with frontier models again because M2.5 can’t follow instructions and misses so many things, as well as being hideously slow. Sonnet (at 10x the price) does so much better, but trying Kimi K2.5 and GLM again in the hope we can find a better medium
You can probably guess what the "niche language" is 🐪
I'm speaking at Sydney AI Engineering meetup tomorrow (Weds) night on using niche languages and frontier models with AI coding tools
www.meetup.com/sydney-ai-en...
Very excited to see ocaml 5.5 in alpha - relocatable Ocaml fixes so many workflows
Iterating on coding guidelines for OCaml that prevent an LLM from horrible nested blobs of match statements.
congratulations! My February edition only just arrived in the post, so I'll be sure to keep a look out for this one next month 😆 (or just read the digital edition like a normal individual)
Bravely entered the beating heart of the AI hype machine (AgentForce Conference)
According to the same recruiters, there are few permanent DevSecOps roles showing up, so presumably those companies have deluded themselves into thinking that CI/CD and good testing practices are a one off investment for leveraging AI
The consulting market is going nuts for DevSecOps at the moment, which can only mean every company is cranking out code with AI but they’re desperately trying to uplift their automated testing and deployment processes to catch up
It made a lot more sense when they started talking about Jane Street, but they don’t have offices in this part of the world.
A recruiter asked me about my OCaml experience today as if it was a regular thing that people hire for in Sydney.
The beautiful thing about AI is it’s ability to produce brilliantly written but historically and logically broken walls of text masquerading as think pieces