

Haven’t heard that frso downplays settler colonialism. Can you help me understand where that claim comes from? I’d like to investigate it further.


Haven’t heard that frso downplays settler colonialism. Can you help me understand where that claim comes from? I’d like to investigate it further.


Trust is relevant in the same way it’s relevant with old school blueprints, dependencies, and with other automation.
In my experience the LLMs don’t consistently get closer.
A puzzle generator doesn’t need to be thousands of lines of code by any stretch.


I don’t think a crossword puzzle generator requires all that much context. Maybe they will get there at some point. They are still consistently confidently wrong, which makes them feel super untrustworthy to me. If a coworker said to me “oh, you’re right, this fixes it” 4 times in a row without fixing anything, I would not trust that coworker. LLMs do the same thing.
You can’t even run them if you don’t have enough system ram, but yeah, graphics vram is for sure very important.


Local models are the ones that have appealed to me the most, but even with 128GB of RAM I can’t run the models I wanted to run like the latest qwen model, which was a disappointment for me. A crossword puzzle generator has been my metric for testing them and I’ve never seen one able to create it from scratch. They’ve gotten much better in the past couple years, but are still incapable of what I consider a pretty basic challenge.
I’ll probably get the itch in a month or two and try the latest local models requiring no more than 128GB RAM and 24GB GPU produced by China.
My coworkers all use anthropic and openai based models so they will absolutely get trashed when the capital subsidies stop. Definitely you’re right that the Chinese models aren’t bound by the same financial scam.


I reject them because they are not useful to me, not dogmatically because I don’t like them. I periodically try them and continue to be unimpressed. I’ve watched my coworkers become increasingly dependent on them - unable to even accomplish basic tasks without them, and ignoring the fact that they are priced cheaply only temporarily. Their speed of code writing is either unchanged or barely increased, and they’re all far slower than I am even with their LLMs.
The output of the LLMs is also unmaintainable, especially when it comes to the test files they write using them.


Meh I am software engineer and am completely unimpressed by LLMs and even more unimpressed by those of my coworkers who have adopted it.


I was having trouble recently, too, after a long hiatus, but I established a goal to read 30 minutes a day 4 out of every 5 days. That seems to have helped me significantly.
Reading through the original article, I think I heard folks near me express contention over this author’s work. I will continue with a special eye to the topic. Thank you for sharing!