tired_and_awake

I wonder if internally they still have their agents writing nonsensical long essays for PR descriptions. We've yet to figure that out inhouse...

Nominally, releases gate it

Years ago I was an academic peer reviewer and hated it, you've probably seen published work thats low in quality - you wouldn't believe how low quality the unpublished crap is. I cannot even imagine the absolute bundle of garbage that must be handled by these unpaid reviewers today. We need a better system.

Would you advocate for the removal of calculators to fix this problem?

This is exactly the right analogy. Granted LLMs are a more sophisticated calculator and engineering is still adapting to this wonky/evolving technology. But to pretend it's a coming catastrophe is to ignore every past parallel development - where this has not happened.

I spent a decade in robotics and have built firmware for dozens of devices. And yet I was never able to successfully fix my webcam device driver on linux with Claude. I'm jealous of this person's prompting skills! Or perhaps pwning is easier than fixing the nightmare that is Intel open source device drivers?

I feel as if a lot of this what Google home (or other "home like" products) could have been and they have failed miserably. As a Google home user I find it can't answer the simplest questions that would require even the hint of an integration within Google's own ecosystem.

I am right there with you. We might lack the language to describe this emotional state; its like the opposite of FAFO? There's also this nuance that they were acquired by meta so yeah they're rich but now they're working for not-serious people and will flame out in 18 months.

I feel for you. Hopefully your colleagues come around and realize that if they submit the code they are responsible for the slop.

Hey just wanted to thank you for the healthy back and forth! I respect your opinion and don't hold mine strongly. That said I'm eager for this space to mature and for us all to figure out the best way to interact with fault prone code generation tooling... Especially at scale where we all have the hardest time navigating complexity.

I think this misses the point, see the other comments. Fully scaled agentic coding replaces managers too :) cause for celebration all around

Completely agree and great points. The conclusion of "agents are writing the tests" etc is where I'm at as well. More over the code quality itself is also an agentic problem, as is compile time, reliability, portability... Turtles all the way down as you say.

All code interactions all happen through agents.

I suppose the question is if the agents only produce Swiss cheese solutions at scale and there's no way to fill in those gaps (at scale). Then yeah fully agentic coding is probably a pipe dream.

On the other hand if you can stand up a code generation machine where it's watts + Gpus + time => software products. Then well... It's only a matter of time until app stores entirely disappear or get really weird. It's hard to fathom the change that's coming to our profession in this world.

The moment all code is interacted with through agents I cease to care about code quality. The only thing that matters is the quality of the product, cost of maintenance etc. exactly the thing we measure software development orgs against. It could be handy to have these projects deployed to demonstrate their utility and efficacy? Looking at PRs of agents feels a wrong headed, like who cares if agents code is hard to read if agents are managing the code base?

Early adopters will early adopt. They will toil,feedback, improve, repeat. Tools will over optimize then dramatically shift based on learnings.

This chaps will continue until something moderately productive and easily adoptable comes out. FOMO will strike all of us from time to time. Some of us will even try out the latest and greatest and see if it sticks.

Some companies will mandate arbitrary code generation standards because "it's the basis of their success", it will polarize their talent pool. Later, it will be impossible to determine if they were (not) successful "inspite of" or "because of" such wild decisions.