RandomWorker

Yes, but… LLMs scraping your stuff can probably only be prevented by the big social media. However, that is some kind of immorality which is cool.

It’s fine tuned minstrel model based on orca Microsoft model.

I've got a 3.xBIL model running on a 8GB version which is fine-tuned to be better than 13BIL models; heres how I did it: https://christiaanse.ca/posts/running_llm/

This is interesting; I've written how I set it up here; https://christiaanse.ca/posts/running_llm/

No, that’s the whole point of running this stand alone without anyone spying.

I’m running mistral 7B on a M1 Mac 8GB just barely. It’s ask a question get a coffee type of thing. No idea how this works, as 32 bit floats require 4 bytes and with 7B it would need to be swapping with the SSD.

If I had the cash I would go for 24GB M2/3 pro. That would allow me to comfortably load the 7B model in to ram.

Seems similar to some Linux distros business model, give it away for free but the service is paid.

The fact that this video has less than 1000 views is insane. Probably not likely to stay this way now it hit the front page. However the audio is quite poor.

Really the problem is with the headline, which is probably all most people will see and read. The title should probably say TVA improves cancer fighting immune system. Is dairy and beef the only source ? My sense is no.

https://pubchem.ncbi.nlm.nih.gov/compound/trans-Vaccenic-aci...

Reviewing pubmed it seems to be a product from ecoli.

Do you have any resources where I could learn more about these networks?

Went to Dutch and Chinese. But only one match on feminine and non on masculine. Sad for me!

Pass it into chatgtp see what it comes up with.

Clojure has a lot of these “finished” libraries and and another functional language like Elm really never gets any updates because it’s considered “finished”. Maybe it’s a functional programming language thing.

When I search Python on the page I find no results?

I’m still using it. It was a rough start but recently I’ve seen some really amazing treads and the crew of people I follow are still there. I think it’s still a great social media better than Facebook feed, and more specific and current on the topics I enjoy reading about than instagram or LinkedIn.

Chess is here, people believe the engine is all knowing and 20+ moves opening “theory” is basically accepted because people accept that engines know more about the game of chess than any human will ever know.

Why not the Answer to the Ultimate Question of Life, the Universe, and Everything?!?

Luckily you can get the https easily. I’ve been using https://letsencrypt.org/ to get it encrypted. Was fast and free. No real barrier just a bunch of setup.

I don’t know who said it, but an amazing quote I love is: “they call it AI until it starts working, see autocomplete”

I love this because when a company tells me they do AI (as a software engineer) they tacitly say that they have little to no knowledge of where they want to go or what services they will be offering with that AI.

My sense is that these techniques would speed up performance on any hardware platform but Intel just got to them first. Good for them, god knows they need all the help they can get.

An eruption is not imminent, however its concerning as earthquakes are increasing in frequency and magnitude.

My sense is to avoid this have a personal blog.

That being said how many people write blogs with grammerly or chatgpt these days. The temptation to use these technologies all the time is too strong for even self preservation of your own (writers) voice.

My sense is that you use this technology you might be happy with the results at first but on later review you just notice something off in some sentences and maybe it just doesn’t flow right. I’m not convinced that it will replace writers jobs yet. Especially when you want to create something authentic and unique.

Any evidence for this?

The ergonomics won’t work for me. I’m sure to sit comfortably I’ll have my chin where the top of this pillow is.

This is a hilarious and fun take on ChatGTP. I can imagine that at some point we have deployed so many of these technologies that we might start living in a Terry Pratchett novel.

my recipe:

1 lbs jalapenos, 4 cloves garlic, 1 tbsp of salt, 2 tbsp of sugar, 1/4 cup water

blend - wait 6-7 days on the counter - check every day for bubbles.

simmer 15 min, 1/4 vinegar added at the end. Strain through a mess for less grains.

put in a bottle. I like it less sweet, but still enjoy the fermented taste. Getting a solid bottle is important.

I like it, but what if we train a neural network that remembers all the data in its weights? My sense is that these companies are using large (deep neural network) models to make their recommendation systems work. We can't ask the neural network to selectively forget a person, at least to my ability.

This was fascinating, and also a nice check. I think I'm over optimistic on A.I. which showed in my score.

He is getting cash from this endorsement. The prices range from 400-3000 CAD. That’s insane for between 3 to 6 patches..

This is basically week 3 of Andrew Ng neural networks and deep learning course on Coursera.

Everyone loves to look at solar, but onshore wind is about 30$/MWh [1]. So we are very close to having that price tipping point.

[1] https://ourworldindata.org/grapher/levelized-cost-of-energy?...