[onion2k]

People think otherwise with AI partly because Anthropic kept telling us that they didn't have to write code or review code any more for most of their work.

Even if that were 100% true, it only collapses the coding effort to near zero. Anyone who's built and shipped a real product should know that coding is maybe 50% of the work, and on a mature product it can be much less.

[DanielHB]

I work on a 10+ year old codebase, there are some weeks I barely change any code.

Sometimes it takes hours of discussion and tracking down decision-makers just to figure out what the intended behavior is.

[skydhash]

And even when you can easily find the intended behavior, you need to trace the modules that relies on the current behavior, especially if the change is located near the core of the software.

[vips7L]

AI fans would say “this is what the spec is for”.

[vanuatu]

even boris says they need people with judgment to manage the agents

i dont write code by hand anymore but shipping something people want is as hard (or maybe harder?) as its ever been

[hintymad]

Boris also says he stops using /plan, he writes loop to write prompt, and he simply asks AI to come up with solutions. He also said many times that his agents would comb their emails, slack channels, and Github issues to come up with things to do. When we combine what he has said, it's hard not to have the impression that he was implying full autonomy of their agents. The only that the engineers need to do is to build harness and to issue approvals, rejections, or suggestions.

[vanuatu]

Yes, there will always be some human bottleneck when it comes to abstract software

i also run loops that comb through slack / github to auto-propose a fix & have another agent auto-review, but you need the human to stamp, and they fail in subtle ways architecturally

[sam_lowry_]

Boris who?

[whoodle]

Not OP, but I assume he means the Boris Cherny, the guy who made Claude code and is a micro-celebrity in certain developer circles now because of it.

[abustamam]

I work on a toy project that has exactly one user (me). On its face it's fairly simple. It's a portal to my media server because I didn't like how Plex worked with regards to searching and filtering. I can look for movies or series by director, studio, publisher, etc. I can rate things, I can find highly rated things. It's great, and instead of bugging plex support to add new features, I just tell Deepseek to do it. I started it before LLms were prevalent and now that I have open code I've had Deepseek write and rewrite most of my code and implement new features.

But even with this toy project, and the target market being someone I should know very well (me), I often struggle to figure out what I want the app to do. When I go through brainstorming or grilling sessions it'll often ask me a question about how the product ought to work and I'm just like ¯\_(ツ)_/¯ give me suggestions and I'll let you know.

[altmanaltman]

Genuine creativity is something LLMs struggle with and it kind of makes sense given their design. If you have a complete plan for a feature or even just an idea what the feature should do, that is enough for an LLM. But asking it to think and come up with a new feature idea by itself will always yield mostly extereme basic things you've already thought of. That creativity of "what" to build so it serves a purpose is still very difficult imo and LLMs are not good at it.

[Forgeties79]

This is exactly why I have no interest in LLM created music, stories, movies, etc.