imgyuri

the way compaction works is pretty simple and highly relies on another model to do it, the only part the user has control of is when to do the compaction, which actually means when doing large amount of work in one shot, it should be planned from the beginning to be separated into works that can be reviewed, afterwards the model can compact

How can the overall trajectory length be the same across reasoning efforts? I don't see how this is possible even if reasoning is not included in the trajectory length calculation.

agree on the quality, there's a reason it usually shows up top in the search results

because there are multiple abstractions in software that one is bound to come across once the software becomes complicated enough, and from that point on "passion" and "fundamentals" determine how effective they are at navigating that path

does anyone know how the new window shows the original terminal instead of the browser? do i need to switch the profile each time?

> And learning modern React ecosystem from the scratch is no easy undertaking even for experienced developer.

I don't see a scenario where this is likely, other than if you're contributing directly to the react codebase.