Googler opinions are my own.

If agentic coding worked as well as people claimed on large codebases I would be seeing a massive shift at my Job... Im really not seeing it.

We have access to pretty much all the latest and greatest internally at no cost and it still seems the majority of code is still written and reviewed by people.

AI assisted coding has been a huge help to everyone but straight up agentic coding seems like it does not scale to these very large codebases. You need to keep it on the rails ALL THE TIME.

Yup, same experience here at a much smaller company. Despite management pushing AI coding really hard for at least 6 months and having unlimited access to every popular model and tool, most code still seems to be produced and reviewed by humans.

I still mostly write my own code and I’ve seen our claude code usage and me just asking it questions and generating occasional boilerplate and one-off scripts puts me in the top quartile of users. There are some people who are all in and have it write everything for them but it doesn’t seem like there’s any evidence they’re more productive.

Just wanted to say I've felt very similarly recently. Honestly feels like we need a place to continue to discuss post-tech career paths for mid-career engineers.

I've been considering becoming an electrician but it is also quite a career shift.

Restarting a career seems so hard. Looking at engineering programs and having to spend thousands just doesn’t sit well. I suspect many of us will just keep doing “software” until they won’t pay us anymore.

That's currently my plan. I have kids, so I need to squeeze software dry.

That argument seems completely nullified by the fact that the president unilaterally changes his mind on tariffs every other day and setting up a manufacturing basis can take 10+ years.

Seems safer for many business to just continue to operate outside of the US and get a more consistent business relationship with every other country in the world.

I hate to say it but I completely agree, don't want to be a downer I'm sure OPs project is cool, but I legitimately could not understand what it was based on this landing page. No videos, demos or details.

This is a really great idea going to try this out. I similarly just cannot mentally stand reviewing vibe coding PRs all day, but this sounds genuinely useful.

This idea sounds somewhat flawed to me based on the large amount of evidence that LLMs need huge amounts of data to properly converge during their training.

There is just not enough available material from previous decades to trust that the LLM will learn to relatively the same degree.

Think about it this way, a human in the early 1900s and today are pretty much the same but just in different environments with different information.

An LLM trained on 1/1000 the amount of data is just at a fundamentally different stage of convergence.

This isn't exactly an answer to your question but I've experienced some efficiency gains in using AI agents for pre-reviewing my PRs and getting it to create tests.

You still get to maintain the core code and maintain understandability but it helps with the tasks the take time that aren't super interesting.

There is a phrase I've heard a number of times in my career that I find relevant here.

"There is nothing more permanent than a temporary demo"

Googler, opinion is my own.

Working on our mega huge code basis with lots of custom tooling and bleeding edge stuff hasn't been the best for for AI generated code compared to most companies.

I do think AI as a rubber ducky / research assistant type has been overall helpful as a SWE.

This is literally it.

High upside (if the AI manages to complete the task it is a time save), relatively low downside (not getting stuck in these AI feedback loops that are ultimately a time waste).

Seems odd to me that people spend so much time promoting some of the least productive aspects of AI tooling.