monatron

I would assume that they would fold this type of classification into their responses API next to existing ancillary tooling that they already ship. I think OpenAI positions themselves as being wholly focused on AGI - but I think their business model leans towards lock-in via superior tooling (Codex, ChatGPT, etc.). This feels like an easy win for them without muddying the larger vision.

This was the first thing I noticed as well. It was refreshing to read.

I think your last point is exactly why I'm so interested in local models. The current landscape doesn't feel sustainable. The last few months we've seen the big providers (OpenAI, Anthropic) start to play with usage limits, resets, banked resets, pulling models, etc. I think local models are close to the point where, with a sufficiently well-architected harness, you can get results that are on par with the experience you'd have with cloud inference. It is nice to know that I have hardware under my desk that I control with open weight models that I can interact with on my terms.

To be fair, I can think of reasons why you would want to be able to set them in various ways.

- settings.json - set for machine, project

- env var - set for an environment/shell/sandbox

- slash command - set for a session

- magical keyword - set for a turn

Very cool! Would love to know more about the audio processing backend that drives this type of thing

If you're like me you're doing it to establish a greater level of trust in generated code. It feels easier to draw out the hard guard-rails and have something fill out the middle -- giving both you, and the models, a reference point or contract as to what's "correct"

Nice tool - I appreciate you sharing the work!

This is a great use case for sub-agents IMO. By default, sub-agents use sonnet. You can have opus orchestrate the various agents and get (close to) the best of both worlds.

Did you folks roll this yourself? I like the learning platform and was trying to figure out what you've might have used to build it.

Claude will do this. I've seen it create "migration scripts" to make wholesale file changes -- botch them -- and have no recourse. It's obviously _not great_ when this happens. You can mitigate this by running these agents in sandbox environments and/or frequently checkpointing your code - ideally in a SCM like git.

There are a lot of nodes that are pre-built to interact with cloud APIs, but you effectively have an HTTP client available that can reach out to any endpoint. In my case, yes, I make use of cloud APIs and realize the trade-offs wrt privacy. You can hit any internal services you like assuming they're reachable from your n8n server