241 karma · joined August 13, 2024
I use AI daily and frankly I love it while thinking of it from the context of "I write some rough instructions and it can autocomplete an idea for me to an extremely great degree". AI literally types faster than me and is my new typewriter.
However, if I had to use it for every little thing, I'd do it. The problem though is when it reaches a point where I have to use it to replace critical thinking for something I really don't know yet.
The problem here is that these LLMs can and will churn out absolute trash. If this was done under mandate, the only thing I'd be able to respond with when that trash is being questioned is "the AI did it" and "idk, I was using AI like I was told".
It literally falls into the "above my pay-grade" category when it comes down as a mandate.
I really hope there's more nuance to articles like these though. I really hope these companies mandating AI use are doing so in a way that considers the limitations.
This article does not really clue me the reader in to if that is the case or not though.
Is just strange to me that my experience seems to be a polar opposite of yours.
If you're not running it on your own hardware and completely offline it's not private. I can prove that.
What these LLMs continue to prove those is they are no substitute for real domain knowledge. To date, I've yet to have a model implement RAFT consensus correctly in testing to see if they can build a database.
The way I interact with these models is almost adversarial in nature. I prompt them with the bare minimum that a developer might get in a feature request. I may even have a planning session to populate the context before I set it off on a task.
The bias in these LLMs really shines through an proves their autocomplete properties when they have a strong bias towards changing the one snippet of code I wrote because it doesn't fit in how it's training data would suggest the shape of it's code should be. Most models will course correct with instructions that they are wrong and I am right though.
One thing I've noted is that if you let it generate choices for you from the start of a project, it will make poor choices in nearly every language. You can be using uv to manage a python project and it will continue to try using pip or python commands. You can start an electron app and it will continuously botch if it's using commonjs or some other standard. It persistently wants to download go modules before coding instead of just writing the code and doing `go mod tidy` after (it literally doesn't need the module in advance, it doesn't even have tools to probe the module before writing the code anyway).
RAFT consensus is my go-to test because there is no 1 size fits all way for you to implement it. It might get an in-memory key store system right, but what if you want it to organize etcd/raft/v3 in a way that you can do multi-group RAFT? What if you need RAFT to coordinate some other form of data replication? None of these LLMs can really do it without a lot of prep work.
This is across all the models available from OpenAI, Claude, and Google.
Which model were you using? In my experience Gemini 2.5 Pro is just as good as Claude Sonnet 4 and 4.5. It's literally what I use as a fallback to wrap something up if I hit the 5 hour limit on Claude and want to just push past some incomplete work.
I'm just going to throw this out there. I get good results from a truly trash model like gpt-oss-20b (quantized at 4bits). The reason I can literally use this model is because I know my shit and have spent time learning how much instruction each model I use needs.
Would be curious what you're actually having issues with if you're willing to share.
Edit: also as the other guy points out, you're going to get different results depending on the model used. llama3.2:3b works fine for this, probably because Meta pirated their training data from books, some of which are probably scifi.
Right now the url is site.co/coparenting.
That’s .co/coparenting
What I’m saying is this works too: .co/parenting
It’s just irrelevant linking linguistics that I’m pointing out that was a missed opportunity. Doesn’t truly matter though.
Also regarding Quarkus, that's java stuff. I don't use it, but I know people do use it for shortcomings of Java in k8s. Perhaps GraalVM is the thing that makes it worth-while, idk.
There's also a distroless Java container from Google that could be of value.
I'd recommend checking out Leslie Lamport's work, you can probably derive some ideas. I'm not be prescriptive here because this isn't a space I plan to work in to solve problems since it's just games. Entertainment isn't really my thing, I tend to lean heavily into systems and security knowledge which has served me well broadly.
As I mentioned in my last comment, someone would need to design a system to better deal with this type of stuff. The way things are stem from decades of decisions made, starting with more design constraints than we have today.
I noticed on the site the really cool animation you got has a 1px solid border on one of the overlays in firefox. Figure you might care since it's clearly supposed to be flashy.