daniel-sc

Resonates well. Only it glosses over the detail that abstractions are often leaky and even increase global complexity for the goal of reducing local complexity of one component/layer. This is where the math example is misleading in relation to software engineering.

I built this for my own problem. I'm bad with names, but when I see them or get some little hint, I snap back in. Maybe it's helpful to others too.

This is a local-first PWA without login or any other burden that lets you quickly note people you met and fear you'll lose their names. Later you can quickly search for them or scan the list to recognize their names.

Any feedback welcome :)

I never installed any "secrets scanner", because of fear it might mess with legitimate tool usage / model context in unexpected ways.

The primary goal of this tool is to adress this. So all "smartness" is in the (human controlled) setup with heuristics helping finding relevant secrets. A plain config file stores references (not secrets themselves), and the runtime harness hook resolves these values and does a literal search + replace for LLM bound text.

Example: It does not block reading `.env.local` but only redacts secrets that were configured in the setup step. This way, the relevant config values can be read by the LLM (and probably the LLM has less incentive to work around to read the full file anyways..).

This intentionally does not cover all ways secrets can escape (direct exfiltration to third parties, transformed values - e.g. base64, unknown secrets, ...) - but I think, the value of "not being afraid to get obstructed" would outweigh that. Also, accidental disclosures shoud be covered rather well.

Currently Claud Code + experimental Codex, Copilot, OpenCode support. Runs fully local and is free and open source.

Let me know: Why would you (not) use it?

100% But this is a major shift and it is totally unclear how to judge/measure „good explanation“. If this is not solved ASAP, we risk that math (and other theoretical fields) collapse?

While I generally agree, the analogy to chess/speedrunning is not convincing. Math is not some hobby/sport, but these new ideas generated often are really relevant for advancing further.