s0ck_r4w

The idea here is that your conversation is being swapped out for no good reason. The session is still active, as the subagents continue to make progress.

How is this comparable to going to lunch or taking a walk?

How do a few extra requests with the same prefix make it more expensive for everyone else?

Make the cache TTL more adaptive. Have more tiers than just 5m and 1h. Long-running subagents become increasingly ubiquitous. There's no reason for Anthropic to not do a better job for this use case.

When using API keys the default is still 5 minutes. Setting 1 hour for the entire session is actually a lot more wasteful considering the 2x rate that it comes with

You can set the retention globally (whole session) to 1 hour which will actually make it more expensive. The default is 5 minutes.

*UPD:* actually it appears the default is authentication-dependent. API key gets 5 minutes, subscriptions - 1 hour.

Do we give them 24 or 48 hours before somebody hacks their service?

I still don't get. The author calls these "Not MVPs. Not prototypes. Working products", but how many users do these "products" actually have?

Have they iterated on user feedback? Have they fixed obscure issues? Made any major changes after the initial version?

More importantly, can the author claim with a straight face that they no longer need to read or understand the code that has been produced?

Just another one of those “look, I built a greenfield pet project over the weekend, software engineering is dead.”

Difftastic seems like a really cool tool. There are a few reasons, however, why it doesn't apply well to use cases I had in mind:

1. It's in JS and not Python. These days a common data (including data tooling) stack revolves around Python and fitting JS into this ecosystem is not straightforwad.

2. Limited dialect support. As far as I can see it only supports "PostgreSQL flavor" (not sure what exactly is meant by "flavor" here). Support for dialects like Spark, Trino, Hive, etc SQL was crucial.

Definitely a worthy mention, though, thank you!

Hey folks! One of the authors here. Somehow this post went under our radar. Thank you all for your comments and feedback! We're super excited about the amount of attention that this project has gotten. This motivates us to work even harder and to deliver even more cool stuff. Go and JS support are definitely on our agenda. Shouldn't be too hard to add since we first transform models into AST and only then interpret AST into a specific language. I might be wrong but this is a very crucial detail that distinguishes m2cgen from similar projects like sklearn-porter. As a result models are completely decoupled from languages and can be worked on independently. Once you implement a particular model, all languages get its support automatically. And vice versa. Plus we support XGBoost and LightGBM :) SVM support is something we'll be focusing on from the modeling side of things. Any contributions are much appreciated!