It’s incredible to come online every day and read breathless articles about how the future is here on the same 5 apps, using the same crappy sources, with the same horrible ad content.
Say what you want about the dotcom bubble at least websites were new. Besides the chatbots nothing feels new or better at all
In my experience what you’ve described as the ideal setting for Eng work does lead to a very high quality product. The problem then is understanding if the market you’re in values high quality over speed or familiarity. All markets claim to value quality, many markets don’t.
Well, there were milestones and docs and extra scaffolding that the gsd system produces, but yes. and it didn't seem like progress was going to go any faster.
Update: I finally got more weekly credits. 5% of codex 5.3 high 1 shot the small project just fine. Like... maybe the consumer harness engineering isn't there yet or codex is just cooking.
At a shitty company. The problem is - you cannot ship a large amount of code quickly in a perfect way. Positioning the problem as "what's the point of generating all this code so fast if I still need a warm body at the end making sure it's OK?" is hilarious.
Don't do that. Just ship it. Yes, good tests, linting, etc will help but if you really believe you don't need humans in the loop at all, at least for the time being, you are fucked.
But go ahead, buy the hype. Your agent swarm can build an operating system in 15 minutes and everything will just work. Cool.
Abstractions truncate the decision space of the layer above them by making understandable trade offs. LLMs don’t abstract anything, your code is still in python or php or Go. It just feels like they abstract if you don’t understand the output since not understanding the layer down is what we associate with non-leaky reliable abstractions. LLMs are abstractions the same way that your code editor is an abstraction- it’s not a layer, it’s an interface.
reply