What I've found is that AI allows lazy and incompetent developers to be more lazy and more incompetent. This then has the effect that product quality suffers more, faster. As a result of the sheer amount of code now being pushed out, code reviews, a thing that previously somewhat prevented lazy and incompetent developers from pushing out horrible code, is effectively dead in the water since no human can actually review such amounts of code realistically anymore. Some companies have adopted AI to review code, which, well ... you have AI make code, AI review code ... I hope you can see the stupidity here if you expect to see any deterministic results at all.
I guess time will tell if the consumer will adapt to the lower quality of products, allowing companies to justify the existence of lazy and incompetent developers, or if the consumer will push back, forcing companies to increase the quality of their developers.
Note: I use AI every day and it is entirely possible to create high quality software with it, so long as you are not lazy and incompetent.
"optimize this code", "fix this code", "extend this code", "add this feature", "find errors and patch them", "find bugs and fix them", "rewrite this from python to rust".
This is all that's needed to actually use LLMs nowadays. How is it a "multiplier" rather than an "equalizer"?
In optimizing my game I noticed framerate hitching even after efficient algorithms were in place for expensive stuff, which was caused by shaders not being precompiled consistently or assets not being preloaded in time. The Agent who'd been profiling and optimizing had moved many preloads to a loading screen, which caused a long loading lock, and what it didn't move ahead was loaded and compiled at use, creating slow frames since work was being done on the main game loop.
I instructed the agent to create a speculative pre-warming/compilation priority queue with a per-frame budget, with priority being determined by likelihood signals that the asset or shader will be used soon. Then I had the AI run fully headed games and hunt down causes for frames going over 16ms, and work through them until a batch of games had fewer than 1/1000 frames >16ms and no frames over 60ms after a short initial settling period.
The approach, the metrics, the validation system and the loop were "prompt engineering" above and beyond what I would expect from someone who was merely "vibe coding a game."
askonomm · · focus · HN ↗
I guess time will tell if the consumer will adapt to the lower quality of products, allowing companies to justify the existence of lazy and incompetent developers, or if the consumer will push back, forcing companies to increase the quality of their developers.
Note: I use AI every day and it is entirely possible to create high quality software with it, so long as you are not lazy and incompetent.
hanifbbz · · focus · HN ↗
rfgplk · · focus · HN ↗
This is all that's needed to actually use LLMs nowadays. How is it a "multiplier" rather than an "equalizer"?
CuriouslyC · · focus · HN ↗
In optimizing my game I noticed framerate hitching even after efficient algorithms were in place for expensive stuff, which was caused by shaders not being precompiled consistently or assets not being preloaded in time. The Agent who'd been profiling and optimizing had moved many preloads to a loading screen, which caused a long loading lock, and what it didn't move ahead was loaded and compiled at use, creating slow frames since work was being done on the main game loop.
I instructed the agent to create a speculative pre-warming/compilation priority queue with a per-frame budget, with priority being determined by likelihood signals that the asset or shader will be used soon. Then I had the AI run fully headed games and hunt down causes for frames going over 16ms, and work through them until a batch of games had fewer than 1/1000 frames >16ms and no frames over 60ms after a short initial settling period.
The approach, the metrics, the validation system and the loop were "prompt engineering" above and beyond what I would expect from someone who was merely "vibe coding a game."