Coding agents make it possible to do lots of work in parallel. I always have several (often many tens of) agents working at once, especially when working in Saggar. They might be working across many repositories, or in the same codebase. They write code, run the tests, and commit... then BAM!

I don't think the terminal is going to die.

I think it's finally going to become usable.

I've been building Saggar, a standalone terminal app shaped around projects rather than a pile of disconnected windows.

I've never heard a paying SaaS customer complain that their subscription subsidizes free users.

That's just the model. Those who can pay cover those who can't, or won't. Everyone gets access, and the whole system becomes more useful.

Nobody writes machine code anymore. For a good reason - it's inefficient to write. Luckily, we don't need to, because somebody already wrote it for us.

lif Shafak says she finds it easier to write sorrow and grief in Turkish, her mother tongue, and comedy and satire in English. The observation lodged with me. If English is hospitable to humour in a way other languages aren't, the question is why — and one answer is that the language carries the structures of British comedy inside its own vocabulary.

A lot of new AI coding tools are built around the same idea: start a thread, keep feeding it work, and let it run forever. You can see the assumption hardening into product features: Claude Code lets you name sessions, find and resume them by name, branch them, and export their transcripts. Cursor has editable chat titles, stored history, Markdown exports, and a way to pull old chats into the current one.

I gave a talk at Write The Docs London a few weeks back, to a room full of technical writers. The pitch: most people's relationship with AI stops at the chat box, and for docs work that's leaving a lot on the table.

I know an alchemical art
which is as ancient as man.
Do you see transformation
on the lines I scratch?
There is an illusion of creation,
but it is just humble change.