I do feel like LLM's start to match certain personalities and characteristics of users which makes them unattractive to others. I assume we will need a better kind of personalization layer in the future or the ecosystems will start to drift. For example I very much feel like grok fits my thought patters by far the best.
None. I find the quality and mostly left wing bias in the current state unacceptable. Too little neutral reporting and way too much subtle opinion making on the current thing.
Without irony, I actually find the South China Morning Post probably the most unbiased, straight on US news.
It also acts as a filter for important US events since they aren't motivated to put out 24/7 bullshit like US based news.
Major US news organizations, be it right or left leaning are just complete trash. Not much higher standards than the National Enquirer at the grocery check out line.
I can't blame the news organizations though since news/politics have become a type of dominate team sport for entertainment in the US in the last decade. Really only second in popularity to the NFL.
Having lived in Hong Kong for a significant portion of my life, I have a soft spot for the SCMP. However it is owned by Alibaba now, so effectively an arm of the CCP.
Use it wisely to bias western propaganda with eastern.
Have you spoken to any Moscovites about living standards recently? Like this is so stupid. I would not trade for Russia's brutal treatment of dissidents but we don't exactly have a great record on that front in Western countries…
I love it how the American DOGE seems to spawn many DOGE movements in other countries too. People are finding and uncovering similarly ineffective spending in a lot of places.
Yes, but if you aren't careful you will end up with a model carefully tuned for be ways that you add noise not all types of noise from the real world. But stuff like this can be very useful for some base training especially if you add many real-world examples afterwards.
It's very much the reason vscode is successfull in my opinion. They differences between local and remote development start to disappear. This is especially useful in corporate environments, but not exclusively so. At the same time vscode keeps the input latency as low as reasonably possible. It's not the best in the world, but the most integrated. And the cherry on top is the out of the box connection loss handling. Just reconnect some when later exactly where you left it.
I tried something similar myself but failed on wanting to load the whole world of openstreetmap onto my server and into postgres. It worked but I never managed to get sub second postgres query times on a billion rows. Hence, making it unsuable for any user.
So my question to you. What's your server and data setup? Do you even have your own data? I'm very curious on what is actually needed to make it work anywhere.
