Oliver Maclaren

first attempt! should be live on repo/npm now...with python/julia/R/haskell/clojure

Ooh good idea!

another little pi extension -- pi-repl (github.com/omaclaren/pi...)

see e.g. www.tandfonline.com/doi/abs/10.1... and surrounding literature. basically have to be very careful to give any sort of frequentist interpretation of fit/lack of fit from ppc as by default don't have standard freq properties. can correct to some extent though

ppc generally have bad frequentist performance…

and focus mode

also

prettied up pi studio (github.com/omaclaren/pi...) with more syntax highlighting and stuff... no idea if actually useful lol but fun being able to make tools like this so quickly with pi.dev (thanks @mariozechner.at )

Me and pi made another pi.dev extension…this time ‘pi studio’: opens a (local) browser workspace for annotating model responses/files, running edited prompts, and requesting critiques www.npmjs.com/package/pi-s...

Haha fair.. yeah I get my extensions kick with pi and leave zed as is (not sure how hard to extend). And yeah re yolo mode but to be honest I was trending that way with the other harnesses anyway

Some others me and pi made: www.npmjs.com/package/pi-c... for critiques and www.npmjs.com/package/pi-m... for nice(r) rendering

Simple extensions like www.npmjs.com/package/pi-a... (by me and pi) are good at forcing me to read and engage with agent code and responses in more detail

pi + codex + zed is the most peaceful workflow for me at the moment. Codex is less sneaky and makes less dumb mistakes than claude, pi lets you add your own little simple workflow tweaks and tools easily, and zed is nice and simple and fast for actually reading code

How tho

I’m too scared for that lol (plus work pays for my Claude sub) so I’ve been using $20 codex mostly

Another one www.npmjs.com/package/pi-a...

pi.dev A terminal-based coding agent

Pi is a lot of fun pi.dev

Got pi coding agent to make itself an extension to render markdown replies with equations in the terminal or browser www.npmjs.com/package/pi-m...

Minimal bash function (add to .bashrc) to generate executable shell commands from natural language. Uses claude code in non-interactive mode (with -p). Can be adapted to other clis easily Minimal bash function (add to .bashrc) to generate executable shell commands from natural language. Uses claude code in non-interactive mode (with -p). Can be adapted to other clis easily - ccc.sh

I missed gh copilot suggest after they deprecated it so here’s a simple bash function to use claude code etc to suggest executable shell commands like it used to gist.github.com/omaclaren/e1... Same deal as eg Simon Willison’s llm-cmd but uses your clis instead of apis

Reading the world beyond your head and it’s talking about my claude code usage

I’m not sure if you need any cc or starting credit for opencode free models! Docs not clear and already gave them a while ago lol…will check again

What's the best 'agentic CLI' tool that is easy to set up with a free tier (no cc details or initial credit req.) for students to use in a university course? Main path I can think of is github copilot student developer pack + e.g. opencode (also just agent mode in vscode...)?

Good shit, thanks

Some lecture notes on spatial and temporal modelling, illustrated using R - darrenjw.github.io/spatio-tempo... - #rstats #rspatial #quarto

Pearl even agrees…

Noticed this (and tried to make the point myself a few time). Not sure about the rest of the paper but agree with this

Olmo 3 is a fully open LLM Olmo is the LLM series from Ai2—the Allen institute for AI. Unlike most open weight models these are notable for including the full training data, training process and checkpoints along …

Olmo 3 is notable as a "fully open" LLM - all of the training data is published, plus complete details on how the training process was run. I tried out the 32B thinking model and the 7B instruct models, + thoughts on why transparent training data is so important simonwillison.net/2025/Nov/22/...

Not necessarily my favourite and nothing on reinforcement learning but does have decision making under uncertainty github.com/omaclaren/op...

Any really good actually insightful or helpful articles or resources on teaching/learning in the age of LLMs?

Gödel Escher BaNAch Spaces