321–330 of 334 posts
“Why are we doing this again?” Is essentially “why are we doing this action a second time?”.
“Why are we doing this, again?” Is essentially “please repeat/re-state the reasoning for this path of action”.
A simple comma, but a significant difference.
Its maybe not a great idea to train models in an environment where subterfuge gets rewarded. Its as if they kept the training rounds that escaped their sandbox, without thinking about which kind of personality those models are then likely to have.
Earlier quoted context omitted.
I’ll try to explain how to do it correctly. I’m not selling anything. Seeing this as the top comment makes me a bit sad. 1. Learn about ports and adapters as an architecture pattern. Domain driven design and locality of reasoning are your new best friends. 2. Realize that AI can generate unlimited fake data almost immediately. So anything you can isolate can get a fake adapter and a real one. You can build and test a…
I honestly feel like you're making this sound more complicated than it needs to be. I get what I would describe as very good results from GPT 5.6 on my projects. There are some methodologies that can improve things for me versus just YOLO'ing but even these are of marginal benefit: * Have good requirements. Experience with a codebase and stakeholders helps a lot here. * Correctly subdivide the task into chunks that w…
The LLMs seem to have no innate ability to understand whats a good direction a higher level. I mean, if you ask them about it, they will actually kinda figure that out, too. But always need that nudge...
So if you as a developer do not have the innate drive to ensure quality, the results will be terrible in my experience.
If you DO spend the tokens on quality though, it can also be kinda awesome. But its not magic.. I notice clear "slowdowns" the bigger the scope gets. They are not actually able to, in any way, subdivide implementations more efficiently than humans.
Earlier quoted context omitted.
Also my experience, it works somewhat ok on large code bases that I designed and built myself before but after months of agentic development they sure start to degrade. I think if you start from scratch with agentic development there is no foundation for the models to anchor to.
I suspect this is just because of context. The AIs have very limited context related to us. I suspect that this is partially a result of the AIs being forced to be highly generalized machines which will work out of the box with anyone's prompt so they can't afford to be tailored to a particular contextual pattern. This lack of a robust pre-defined contextual framework that is relevant to the human who is prompting th…
Its still much better than trawling thrugh code yourself, but they are far from all-knowing. I have to say they have gotten 10x better in just a year as well. Or they are very good bullshitters and just sound confident.
Earlier quoted context omitted.
For my side project where uptime doesn't really matter but the codebase is quite huge (gamedev of a multiplayer game with Bevy, so both server code, game code, content build pipeline, as well as a TON of editor and authoring code, probably 150k+ LoC), I've been moving towards just reviewing boundaries between modules, APIs, and schemas, and I'm pushing towards keeping things as modular as possible. If something ends…
This can easily lead you down a path of excessive modularity with each module being excessively complex though
its contradicting metrics. You either have modules being excessively complex and not enough modularity or vice versa
Earlier quoted context omitted.
You’re correct–you actually can’t improve the model in one area without changing the characteristics in every other area. It’s almost like the whole thing is just a lot of linear regression…
As in you change one parameter and the whole equation changes or something else? (I'm bad at math!)
Earlier quoted context omitted.
People keep saying that "models are just compilers, and I don't see you complsining about compilers". Which is such a bullshit argument
Can you elaborate? Is it because the models are inherently not deterministic? But then, will it not get better with time? I mean arent we just at the beginning of the research here?
Determinism isn't the issue; it's that the prompt does not contain enough information to know the correct way to do the thing, even if it did the thing the same way with the same inputs every time.
> And potentially as a byproduct of enabling all of this, you can now slop your way to a one-shot 3D game over the weekend which looks impressive. I think we've finally reached a weird point where AI has effectively reduced the amount of competition that real game developers have to endure. Nothing unravels faster than a game project being built with AI. You can achieve impressive results in a day, but you can't get…
>> And potentially as a byproduct of enabling all of this, you can now slop your way to a one-shot 3D game over the weekend which looks impressive. Do these games really look impressive? Everything I've seen has looked like someone completely new to Unity/Unreal has slapped together a bunch of premade scripts and very poor 3d assets.
As an amateur game dev who knows some amount of things, honestly, not coping, I have not seen anything come out of AI game dev that would have been more than like one month of human dev work. And obviously, games take a lot more than one month to make...
51 comments so far, the vast majority panning Astra's coding abilities. An uninformed reader may come away with the impression that this isn't an absolutely revolutionary technology that with coding abilities many of us thought were not even going to be possible with language models as recently as a year ago. Yeah, it's not perfect, but it's really good and extrapolating this rate of improvement for 6 months is rathe…
There was a big jump around new year, but they seem to have flatlined since them. Just my experience.
When the code is shitty it becomes harder and harder for the models to make changes and this grinds progress down to a halt - this has been my experience with “factories” trying them and doing refining steps every few months. I sincerely don’t understand what the people who say they no longer read any code are doing, because it must be somewhat trivial to not run headlong into these issues that stack up time after ti…
I am currently writing a lot of code that I am not reviewing anymore. These are all the things that make it work for me: - Work on small projects ( - Work for business people who want fast results. Agentic coding gets you to something presentable much faster at the cost of code quality. I have never seen a customer or business person care about that. - Have clearly defined API boundaries. Examples: If the back end is…