decancode

This is interesting, ideally with checkpointing and other such mechanisms, the long term session recovery will improve.

What does need to be seen is how well the agent works with the recovered context. In certain cases when I was trying to do this locally (using a custom setup), the agent just skimmed through the context and skipped over its own findings before the session crashed.

I do like the code mode though, agents indeed are good at that. In an 80 repo code migration, claude code figured out that the task is going to become repetitive and the patterns are identified, so it wrote a shell script to automate the migration, and itself acting just as a progress monitor

Really hoping this will not strip off messages as it happens in iOS apps with long conversations over days.

Have been seeing that happen consistently where older chats have some messages missing in between

This is one of the biggest problem impacting the development cycles now.

As a Senior IC, the amount of code I have to review every single day has dramatically risen.

Interestingly, so is the confidence of the junior engineers putting that code up for review, because another AI has reviewed the code already.

Not sure, but if this is how things pan out, we are looking at severely degraded softwares shipping to customers, very very soon

But in reality, the real cost of engineering teams grow as the sub organizations and teams continue to make short term decisions, optimizing for the next immediate win.

More common so in larger organizations than smaller ones

https://www.github.com/neuvem/java2graph —- A semantic code graph for AI agents (for Java language)

The goal is to provide AI agents with deep understanding of the codebase and help them understand the context, not just text