We have notebooklm at home? Is there any comparison between these two, looks nice

Thanks for sharing NotebookLM, I hadn't seen that! I'll take a look and add a comparison to the README if it's compelling.

In my opinion, the coolest thing in NotebookLM is the podcast-episode-generator. Each one sounds like two people having a conversation. It's fun to listen to a podcast episode about some niche topic (e.g. nuclear isomers, or the Weyl curvature tensor) while I'm cooking or driving.

insane levels of slop, so bad it almost feels intentional

So they made a phone?

More evidence of the Smartphonification theory. Much like how all life trends towards crab, or all software towards reading mail and including a bespoke Scheme implementation, I posit that all hardware eventually becomes a smartphone.

Examples: - the cellphone (obviously) - my TV - my refrigerator - my oven - music players - tablet computers - laptops (well on their way) - cash registers->PoS sales machines - handheld game consoles

> Much like how all life trends towards crab

Carcinisation (https://en.wikipedia.org/wiki/Carcinisation)

The same seems to be true for trees too (arborescence).

A full Linux phone with an M.2 slot, Ethernet, hardware buttons, SDcard etc.

This is what you've all been asking for, right?

I'm more excited for qwen3.7 9b and 72b, these are usually so good for their size

also parsing is harder + so much more of the new data is being generated by ai itself.

still the cutoff is very much concerning and inconvenient

benchmarks look REALLY good, the price hike is big but it also beats sonnet 4.6 in every discipline?

you ever look on a title and just immediately know that its going on the frontpage + staying there

There are times where I immediately guess it, the recent mitchell post of AI psychosis was something that I recognized (which is now at 2k upvotes)

But there are other times where I am wrong too and I even comment on threads with less upvotes because the topic is so interesting yet my comment just ends up being isolated.

It's really more like a 50/50.

Even the one post of mine which had reached the front page of Hackernews was something that I absolutely knew could reach front page but then there weren't much responses for a few days but then after a few days, I saw that it was re-uploaded (I think that Hn selects a few submissions which are interesting, I forgot how that mechanism worked) and then I reached the front page of Hackernews ;)

Either way, I think people should just make what they feel is interesting but I remember reading some article once which said a few things which this article follows:

1. I built XYZ... gets more frontpage than we built XYZ...

2. having (Open source) in the title increases the chances too

This article has both of them so its definitely interesting to see it on front page, either way its an really interesting project :-D

if you're not checking citations in the paper youre publishing AND trusting a non SOTA, hallucination prone ai model to come up with sources for it, its probably for the best of everyone that this paper isn't published.

yes there will be rare exceptions but in general i feel like this is a really good addition.

> non SOTA, hallucination prone ai model

What SOTA models are not hallucination prone?

7b mistral is quite outdated. On a 12gb 4070 you can run qwen 3.5 9b q4km or qwen 3.6 35b, the latter will be a lot smarter but also a lot slower due to ram offload.

Try both in lm studio, they really are surprisingly capable

I have 80gb of ram but it's slow capped by i9 CPU or specific asus mobo sucks I think only 2400mhz despite being ddr4

Tried all the stuff bios, volting

Gemma 4 26B-A4B might be interesting to try on your machine. The latest optimizations make MoE models work pretty nicely on setups like that with a decent GPU and lots of slowish RAM. I have a 16gb GPU and 64gb of 3200mhz DDR4 and get 15-20 tokens/sec out of that model with zero finagling or tweaking. I’ve been very impressed by it, even having run just about every other open weight model that would fit on my machine over the last few years.

that seems slow? 15-20, was expecting 50-60 like mistral although I have not measured that yet on my setup

I've been asking other people but what do you use it for?

anthropic really needs to just make a great, personalized customer support experience where you get a couple dollars worth of opus credits that has some authority and ability to help with your issue.

"it couldnt be that simple because xyz" why not? I'm yet to see any big ai company actually try this