I have it running on a Proxmox VM. It basically just sends me summaries -- it reads a bunch of RSS feeds I pointed it to (news, tech, etc) and gives me a daily summary, along with an image of the day based on that. It also sends me recommendations for times to go for a run based on the weather and my Strava activity, daily recommendations for stargazing (what's visible and when, weather, etc), and a couple of daily reminders for things I tend to forget.
I'm using Claude as the model, though, so it's smart but pricey. Should configure it to use different models for different things, but it's trickier than I would have expected to do that.
Wait, that's it? Seven paragraphs, all short? Two quotes, one from some anonymous MS exec? Is the site sending some minimal version of the article to me because I'm using Brave, or is this the lowest-content article I've seen in weeks (and I'm on Twitter)?
It's a bit of a double edged sword. As someone who smoked and found it impossible to quit for decades, I'm very happy to have been able to switch to (reuasable) vaping. It's probably added years to my life expectancy.
OTOH the upsurge in nicotine use amongst young people feels suboptimal, and disposable vapes are a scourge.
Looked to me like it was trying to work out whether it was edible. Sensible behaviour for an animal in a world where unfamiliar edible things appear from time to time.
Not sure that every browser advertises English, but mine certainly does. However, as I'm in Portugal, many websites ignore what my browser says and send me to translated versions, I assume based on my IP. That causes problems because the translations are often quite bad, and they do it with redirects to PT URLs so I can't share links with people who don't speak the language.
Does "advertises" in this context mean what's put in the "Accept-Language" HTTP header? Might be worth seeing what that value specifically is the next time this happens. A "clever" IP-based language choice server-side seems far too complicated and error prone, but I guess that's what makes it so "clever."
Yeah I've seen this a few times on the backend that decides this. The standard should be to use the accept-language header, but all the time when people write their own code on top of frameworks (or maybe use niche shitty ones) they just geoip for language.
For business use cases sometimes it's based on the company's default language that you're an employee for.
Try to use any Google site while traveling. I have two languages in my Accept-Language header, but Google always give me language based on location if I'm not logged in. There are also many other sites that does the same, often without any option to change language
I have the same problem in Argentina. Worse, I'm pretty sure that Google and other search engines decide that I don't deserve to receive good information because I live in a Spanish-speaking country, so they send me to terrible low-quality pages because often that's all that's available in Spanish.
I think the punctuation makes it clear -- imagine "How I invented Facebook. In 2001." The full stop in the middle of the sentence breaks it and makes you realise he's speaking figuratively.
OP here -- with a 112M model you should be able to get something worth playing with using 2.24B tokens. The Chinchilla heuristic is tokens = 20 x parameters. Obviously you cam get a better result by grinding through more tokens, but it will be very slow progress. It's worth noting that Andrej Karpathy is using the 20x thing for his nanochat project.
I try to explain the Chinchilla paper in the post, but your favourite AI should be able to explain it well, and has the benefit that you can ask follow-up questions.
OP here: one thing that surprised me in this experiment was that the model trained on the more curated FineWeb-Edu dataset was worse than the one trained on FineWeb. That is very counterintuitive to me.
I'm using Claude as the model, though, so it's smart but pricey. Should configure it to use different models for different things, but it's trickier than I would have expected to do that.
reply