Close… I’ll download the HTML for an eBay search results page, and then a script splits it up into separate entries and feeds each listing’s HTML chunk to the LLM. I don’t bother with individual listing pages. (This falls down on some edge cases like listings that include multiple variants via a pull-down selection only found on the individual listing page. Maybe a future area of improvement.)

Self host. Just Ollama running on a machine without a GPU! I never said it was fast. :D

Made a product search script that sorts eBay listings based on total per unit price (including shipping). Good for finding the cheapest multi-pack, lot, bundle, etc. by unit. Using Qwen 3 4B and feeding it a single listing at a time to parse.

Excuse me… It was a hand motion that appeared to some observers to be consistent with a historical German sign of greeting and/or eugenics.

/s

Tesla profits are down 71% year-over-year, and the only reason they didn’t actually lose money is due to some carbon credit shenanigans.

Keeps the comb-over from blowing out of place in the wind.

Trump’s outtie enjoys frequent victories in golf tournaments.

You’re both wrong! Judaism is a culture centered around matzo ball soup.

I don’t think either of those are necessarily true. It’s quite likely IMO that the Trump regime just likes the precedent… If they get away with this, it means they can deport and imprison anyone “by mistake” and then claim oopsie daisy, there’s nothing we can do about it.

I’m not defending social media or its algorithms, but you’ve also got to look at what predated it. People used to get their news and information from news anchors and newspapers that were mouthpieces for capitalists and conservatives. So maybe not as extremist or even as effective at influence as a social media algorithm, but still not great. Personally, I don’t want to go back to relying on corporate news outlets either.

Rubio?

Make a puppet of Trump and dress up like Putin. Or Musk, if that’s easier.

If a fact isn’t disputed by either side in a case as contentious as this one, it’s much more likely to be true than not. You can certainly wait for the gears of “justice” to turn if you like, but I think it’s pretty clear to everyone else that LLMs are plagiarism engines.

Lol did you even read the article you linked? OpenAI isn’t disputing the fact that their LLM spit out near-verbatim NY Times articles/passages. They’re only taking issue with how many times the LLM had to be prompted to get it to divulge that copyrighted material and whether there were any TOS violations in the process.

“In its suit, the Times alleges that, when prompted by users, ChatGPT sometimes spits out portions of its articles verbatim, or shares key parts of its content, such as findings uncovered through investigations by Times reporters, or product endorsements carefully researched and vetted by Wirecutter, an affiliate site.”

From: https://hls.harvard.edu/today/does-chatgpt-violate-new-york-times-copyrights/

I generally agree, but I also think it depends on the capital. There are definitely losers (in the winning/losing sense) in the business world even just two months into the second Trump regime.

I think you’ll find that many (but not all) successful movements are driven by the potent pairing of a legitimately pissed off populace backed by capital.

https://en.m.wikipedia.org/wiki/Tea_Party_movement

Guess who makes the money from the chargers though.

Which also benefits from organizing.