I'll check that out - I loved his "The Code Book: The Science of Secrecy from Ancient Egypt to Quantum Cryptography". Excellent introduction to cryptography.

I really liked her "Uncharted with Hannah Fry" podcast, sorry it ended.

FWIW, Cognition has all the Sonnet/Opus/Fable models, and all the GPT ones, as well as GLM, Kimi, and Gemini.

It's not very clear on the website, couldn't find a list of models or quota/pricing per model anywhere

But they don't appear to subsidize them to the same degree. I've only been using Devin for less than a month, but I've been hitting the limits of the $20/month plan way more quickly than I'd expect, and definitely more quickly than with Claude Code or Codex.

So far, Cursor provides the best value for their subscription, but I have to imagine they're basically lighting money on fire. There's no way their current pricing is sustainable.

What "non-house" harnesses have you found to work best?

Interesting to see (roughly!) what percent of each car is engine.

I have this setup, roughly, with UTM rather than orbstack. I think I have it set up safely, curious how you see it has the wrong permissions?

Another way I'm "going slower" is to have the AI implement individual sub-steps of the current task, and review each one. It's slower than having it yolo out the whole thing, but it's much smaller incremental bits to review, so my brain doesn't glaze over in a huge review, like I had if I had it do the whole task.

I'm following an Ideas -> PRD -> Issues -> Tasks methodology, where each task has a bunch of sub-tasks. I have it just do one (or a few, I'm having it do Red/Green/Refactor as separate sub-steps, so I review the Red case, and then once that's good, do the Green and Refactor steps, and review those).

Yup, just like people!

Good!

Nope, not better quality if you don't like the smell of cigarettes.