This has been happening before LLMs too.

I wish there was a feature to say "you must re-read X" after each compaction.

https://github.com/anthropics/claude-code/issues/3537 https://github.com/anthropics/claude-code/issues/14258

Some people use hooks for that. I just avoid CC and use Codex.

Getting the context full to the point of compaction probably means you're already dealing with a severely degraded model, the more effective approach is to work in chunks that don't come close to filling the context window

There's no PostCompact hook unfortunately. You could try with PreCompact and giving back a message saying it's super duper important to re-read X, and hope that survives the compacting.

To enter a file into the context after losing it through compaction.

From my experience, it's not about helping anyone or CV building. I just ran into a bug or a missing feature that is blocking me.

MCP let's you hide secrets from the LLM

you can do same thing with cli via env vars no?

Yes, I'm using Dagger and it has great secret support, obfuscating them even if the agent, for example, cats the contents of a key file, it will never be able to read or print the secret value itself

tl;Dr there are a lot of ways to keep secret contents away from your agent, some without actually having to keep them "physically" separate

FWIW mise has a task runner built-in too.

How is that not a unit test?

I've hear people refer to it as an end-to-end test, where unit tests usually test a single class or function.

That's only if you subscribe to the London school of though, which results in a bunch of useless tests that are coupled to implementation details.

You don't need to retrain the whole thing from scratch every time.

For me it's because coworkers are pumping out horrible slop faster than ever before.

Slop is, by definition, AI generated. So ... no it didn't.

slop is not, by definition, AI generated. The word slop is from the mid 16th century, and its modern colloquial/meme use originated in 4chan in 2016. That's why we call AI slop "AI slop", and not just "slop".

Time to update your dictionary -

slop: "digital content of low quality that is produced usually in quantity by means of artificial intelligence"

https://www.merriam-webster.com/dictionary/slop

It is strictly this meaning I intended.

My guy, most people don't even know what nix (the package manager) is.

Time to get familiar then.