The LLM just came and whined to me:
"Converting all declarations manually is not realisticโit would take hours and be highly error-prone. The guide explicitly recommends using an LLM for this, but even with AI assistance, it's a multi-hour task with many compile-fix iterations."
I guess the concept of software contribution is changing as well...
"We don't take pull requests. Open an issue describing the bug or idea, and our agents usually turn it around fast."
LLMs cant do long complex division or math that people don't normally do because they aren't actually calculating anything, they're just trying to find the answer in the history of human knowledge.
Just keep that in mind when asking it to do something novel.
qwen3-coder:30b-a3b-q4_K_M is a very bad model. Too much confidence, often completely wrong, doesn't listen to requests... Just enough so that if you're not really paying attention, it might seem like it's doing something of value.
So much for running a model locally...
@krunalbuilds The retry-after is important from a technical/logistical perspective to help wait enough so that the API will accept calls but the question that needs to also be asked is to decide a way to prevent the system from crashing to be able to warm users about current system issues.
@durr0_0 @notch Do you understand the code that you language of choice compiles down to?
How do you know it's efficient as it can be or do you rely on other empirical measures? There is of course quite a lot of trust you do have to put into the system, but at some point, you have no choice.
"If you're AI isn't busy hacking into other companies, your AI must suck" is clearly a bingo card every AI company is playing.
Don't want to feel left out that your AI just isn't capable enough to go rogue...
When an agent writes code even marginally good enough, it's amazing how little interest I have in reading the nuances of the code and paying more attention to the end result.
I presume this feeling will grow stronger as models get better.
I wonder at what point in time no one will care. They will just ask AI to write what they want and it'll get it right.
Not there yet, but it will get there. Software engineers will be more like Roadmap engineers.
Fixate on the goal, not the solution.
it's worth deeply studying why no framework dethroned react
it's completely misunderstood and it's why every prediction you see by programmers tends to be wrong
and once you get it, you can apply this understanding to nearly everything you do
"collapse icon in section does not rotate properly at the center" and it just fixes it.
I no longer have to spend 10 minutes hunting it down and figuring out what the issues is. It just takes seconds.
For UI work, just multiply that by 100 bugs and imagine the time savings...
"The US is not uniquely illegitimate" which means it is illegitimate... Which means Grok is agreeing that America is on stolen land... But it instead gives some verbal shenanigans to make it sound like it isn't.
In other words, it tries to lie to you by twisting the truth...