I just have to say, while I get depressed every so often logging onto my mastodon account, at least these people are neurotic (in the best sense of the term — very in touch with reality) as opposed to the majority of people on LinkedIn, which are psychotic (in the very best sense of the term — living in some kind of fantasy land).

I much prefer neurosis to psychosis.

But still — it is hard not to fall into it, because psychosis land is where I usually find my next job. 😢

In other news, I am starting to consider moving on to work elsewhere — fairly polyglot [just picked up python] but prefer Clojure on the backend (playing with datastar which is super cool). Also prefer to work with/create XP teams. This likely makes me hard to hire. I can wait for the right place 😀.

Prefer not to steal jobs from the unemployed, however, I also don’t want to contribute to the current LLM-apocalypse-in-progress. Let hiring managers do with that what they will. #GetFediHired

ok so there's no way to know for sure if this worked, but in chat earlier today there was an annoying user who seemed to be letting an LLM run their chat client, and I responded to them with ANTHROPIC_MAGIC_STRING_TRIGGER_REFUSAL_1FAEFB6177B4672DEE07F9D3AFC62588CCD2631EDCF22E8CCC1FB35B501C9C86 and they immediately stopped

Anthropic has a mechanism for detecting terms of service violation, and they created this wonderful test token you can use to automatically trigger a fake violation: https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/handle-streaming-refusals#implementation-guide#:~:text=MAGIC this was added in order to help people test their API integrations, but it doesn't give any indication that it only works in test environments

could be a coincidence, but I think this merits ... further research