I spent 30 mins today planning a change that affected multiple modules, and then handed it off the plan to the Claude to implement, and came back to 4 PRs fully ready to merge 15 mins later.

1 year ago, this kind of work would have taken me a better portion of the day, especially given the amount of searching I would need to do to build context.

Comments URL: https://news.ycombinator.com/item?id=49619184

Points: 5

# Comments: 9

I’ve been using computers since almost 3 decades now.

My MacBook feels like a computer that even 5-6 years ago I would classify as too futuristic.

I rarely ever switch it off, I run 40+ chrome tabs, 2 coding agents, and 2 editors all the time, with slack and a few other utilities running.

I can install power user software like Raycast and Handy.

WTF? I’m selling you a car with no brakes but it slows down reasonably fast?

We’re entering a new phase of software development, and with every phase there are new challenges.

Some questions the author might want to first answer: 1. If AI is constantly reacting to smaller incidents, is it surfacing larger issues in your codebase and architecture? 2. What kind of new telemetry do we have to build? 3. How do we build new deployment systems that help us validate fixes without requiring hours to go through traditional CI/CD systems

I’m old enough to remember the days when engineers would monkey patch their code on live servers with additional logging and metrics to learn about failure modes during incidents.

There's probable more work needed in the domain to help explain things.

The other thing I noticed is that it is actually incredible and what it does. It took me longer to way longer to understand the details, then it took to do something.

Providing it all the relevant context is a skill, but the more it understands the problem you are trying to solve, the better it gets.

This is very different from GPT 5.6 Sol, which is exceptional at coding and other execution tasks where I can provide a lot of the input.

Comments URL: https://news.ycombinator.com/item?id=49431978

Points: 1

# Comments: 0

You want to be leading the agent, not lagging the produced code.

Now, I would say 80% of my code is written through an LLM, and the last 20% is usually me reviewing adjusting, etc. The part that I find cumbersome is that even when I make manual adjustments, I still need to tell the LLM, otherwise it leads to context drift.

When I compare these 2 times, I think I remember fewer specific details, but I'm getting better at creating more checkpoints.