https://news.ycombinator.com/item?id=45447390

or

https://github.com/A11yance/axobject-query/pull/354

This user actively gets paid off of how many downloads their packages get, which makes sense why there are so many. As well as the attitude to change others repositories to use his packages

I just asked gemini 3 5 times: `what temperature I should take a waterfowl out of the oven`

and received generic advice every single time it gave nearly identical charts. 165F was in every response. LLMs are unpredictable yes. But I am more skeptical it would give incorrect answers (raw goose) rather than your mother preparing the fowl wrong.

Cooking correctly is a skill, just as prompting is. Ask 10 people how to cook fowl and their answers will mimic the LLM.

We are leaning into conspiracy theories / not accepted history but making these marks with the currently thought tools seems quite insensible, and are related to the article. Folks seem to think we have not found the real tools that created these structures. The vertical inward scoop marks are especially suspect.

[0] - https://www.theancientconnection.com/aswan-unfinished-obelis...

[1] - https://www.theancientconnection.com/megaliths/egypt/the-ser...

Going on year 4 working at $DAY_JOB and just last week we had a case where enums and also union types would have made things simpler.

Apple wasting years of everyones time on bad faith UX design

The rest is no longer true, indeed

Are you in a top tier city? Very very few cafes are open late (later than 8pm) in cities and if youre not in a big city, Chicago, NYC, Seattle etc etc you will likely have none open that late. It's definitely a culture thing. Not many folks are drinking coffee / hanging out that late in cafes. Enough do, but nowhere near as much as Europeans do

LLMs writing prose is too robotic

LLMs output is too dependent on prompts to be interesting

LLMs take too much RAM to run effectively

LLMs take too much electricity to run locally

LLMs work locally but are a bit too slow for my taste

LLMs output mostly correct code but it isn't applicable to my codebase

LLMs make tool calls to pull in additional context

LLMs outputted code works for most developers but not my codebase <---- you are currently here

Did the author of this article review it? Is their entire position that to differentiate yourself you have to do lessor work because AI is perfect? Are they suggesting that AI / LLMs are better than humans?