I like to make computers learn things
Joined December 2020
- Tweets108
- Following138
- Followers38
- Likes1.7K
Zach Robertson retweeted
the techno-optimist crowd often assumes Musk and Thiel share the same political alignment because of their backgrounds. in reality, nothing could be further from the truth.
Chat With RTX is a strange experience. Basically just a gradio demo running locally. For someone not technically inclined I think this is a really good way to test out some open source LLMs quickly but it definitely lacks the polish I would have expected from NVIDIA
Can anyone explain to me why Microsoft charged $0.99 for their H.265 codec? That shit wasn't even designed by them and came out in 2013!!!! Who do you think you are Microsoft
Zach Robertson retweeted
New open weights LLM from @MistralAI
params.json:
- hidden_dim / dim = 14336/4096 => 3.5X MLP expand
- n_heads / n_kv_heads = 32/8 => 4X multiquery
- "moe" => mixture of experts 8X top 2 👀
Likely related code:
github.com/mistralai/megablo…
Oddly absent: an over-rehearsed professional release video talking about a revolution in AI.
If people are wondering why there is so much AI activity right around now, it's because the biggest deep learning conference (NeurIPS) is next week.
magnet:?xt=urn:btih:5546272da9065eddeb6fcd7ffddeef5b75be79a7&dn=mixtral-8x7b-32kseqlen&tr=udp%3A%2F%2Fopentracker.i2p.rocks%3A6969%2Fannounce&tr=http%3A%2F%https://xitter.cf/t.co/g0m9cEUz0T%3A80%2Fannounce
RELEASE a6bbd9affe0c2725c1b7410d66833e24
Zach Robertson retweeted
magnet:?xt=urn:btih:5546272da9065eddeb6fcd7ffddeef5b75be79a7&dn=mixtral-8x7b-32kseqlen&tr=udp%3A%2F%2Fopentracker.i2p.rocks%3A6969%2Fannounce&tr=http%3A%2F%https://xitter.cf/t.co/g0m9cEUz0T%3A80%2Fannounce
RELEASE a6bbd9affe0c2725c1b7410d66833e24
Zach Robertson retweeted
I spent some time building this obsidian-meets-chatgpt-meets-tab style application. It can scrape the web when I add a link in my notes, and it will both vectorize and create graph-based relationships for context later on.
I ended up dropping the project for more pressing work, but want to revisit it if nothing else like it exists. Anyone know of something useful that basically does this? Would anyone use this?
(in the example, I'm using my notes and code to query the app about itself. the graph above represents the related notes and tags)
Rewriting my website to move away from Gatsby. Any suggestions on what frameworks I should use? Simple blog style site that I want to keep fast and cheap to deploy
Only the beginning for our Discovery Engine, come check out what it can do at BitSurf.network. it only gets better from here🚀
At the core of BitSurf’s discovery engine is a content-first recommendation algorithm. We forego a virality and engagement driven algorithm because doing so enables deeper and more relevant recommendations than traditional social media websites.
Here’s a simple demonstration.
A blog post shared by Andrej Karpathy details the surprising power of a MacBook’s ability to run Large Language Models.
On the X platform, the discover more feature does not really demonstrate clear information relationship between the original content and the recommended posts.
The same content, indexed on BitSurf, produces a recommendation of a post giving instructions on installing and running an LLM on an M1 MacBook Pro.
The quality of recommendations speaks for itself.
What will you discover?
Zach Robertson retweeted
At the core of BitSurf’s discovery engine is a content-first recommendation algorithm. We forego a virality and engagement driven algorithm because doing so enables deeper and more relevant recommendations than traditional social media websites.
Here’s a simple demonstration.
A blog post shared by Andrej Karpathy details the surprising power of a MacBook’s ability to run Large Language Models.
On the X platform, the discover more feature does not really demonstrate clear information relationship between the original content and the recommended posts.
The same content, indexed on BitSurf, produces a recommendation of a post giving instructions on installing and running an LLM on an M1 MacBook Pro.
The quality of recommendations speaks for itself.
What will you discover?
We have been grinding hard on this @BitSurfApp
Lots of updates coming soon, it only gets better from here
Zach Robertson retweeted
We call this product market fit.
Follow for updates over at @BitSurfApp
This Post is from an account that no longer exists. Learn more
Zach Robertson retweeted
The search experience is fundamentally broken. This is because Google was originally designed for a dense flat internet of honest actors.
Now, the internet is siloed within a feudalistic landscape of large internet conglomerates. Bots run amok, and synthetic content is adding more and more redundant information to the landscape. The web is now far more deep than wide, and search indexes will miss all of this content.
LLMs aren’t going to fix this. The tools to scan and scrape the internet are now a part of a perpetual arms race against those who want to protect their data silos. Twitter vs OpenAI comes to mind.
The way we discover information across the web needs to fundamentally change.
I’ve been building a tool called BitSurf (@BitSurfApp ) that aims to solve this problem. You can make an account for free and try out our early proof of concept for a platform based solution. There’s a lot more to come.
Here’s a great video that further elaborates on the deterioration of search.
youtu.be/48AOOynnmqU
Would love to see someone try out the llama2 7B weights with this inference method to see what the tok/s comes out to. I image it is still pretty reasonable assuming the model can still fit into system memory.
Maybe this is my weekend project
ML moves fast these day
xitter.cf/karpathy/status/168369…
Yay, llama2.c can now load and inference the Meta released models! :) E.g. here inferencing the smallest 7B model at ~3 tokens/s on 96 OMP threads on a cloud Linux box. Still just CPU, fp32, one single .c file of 500 lines: github.com/karpathy/llama2.c
expecting ~300 tok/s tomorrow :)