nand2tetris only requires programming ability at the level of someone who's taken freshman level CS IIRC.

You could take Harvard's CS50 and then tackle it.

We should not cater to people who make decisions based on titles instead of reading the actual article.

That's a shitty rationale for click-bait titles. Good titles are for the benefit of people who actually read the articles too.

What are some examples of this?

CI Builders/QA Agents can do this very well. User session starts, bring VM up with content + dependencies, when session is done throw it away. Keeps it clean, debuggable, fast and cheap.

Could prompt injection be used to trick this kind of analysis? Has anyone experimented with this idea?

Prompt Injections are very very rare these days after the Opus 4.6 update

And software isn't as constrained by physics as hardware, which massively expands both the design space as well as how many ways things can go wrong.

Matt Pocock has a nice TDD skill he's made available [0][1].

[0] https://www.aihero.dev/skill-test-driven-development-claude-...

[1] https://github.com/mattpocock/skills/blob/main/tdd/SKILL.md

She wrote about it in the most recent post on her blog: https://lexi-lambda.github.io/blog/2025/05/29/a-break-from-p...

I think they're talking about cases when you can make the "zero" behave like an algebraic identity.

I had to disconnect Mullvad to load the page.