Sam Rose's banner

Sam Rose

@samwhoo • 19,467 subscribers

That guy who writes visual essays about software at https://t.co/nLO1QnXOPa. Developer Educator @ngrokHQ.

Shorts

I think this is the best post I've ever made.

I think this is the best post I've ever made.

622,832 次观看

Made a tool called llmwalk that shows you the most likely answers an open source model will give you. It tree searches the answer space until it finds the N most likely answers. uvx llmwalk -p "Answer succinctly: when did France first win the world cup?"

Made a tool called llmwalk that shows you the most likely answers an open source model will give you. It tree searches the answer space until it finds the N most likely answers. uvx llmwalk -p "Answer succinctly: when did France first win the world cup?"

88,420 次观看

John Carmack Ooh I made some visuals of the differences in precision of different floating point formats recently for a post on quantisation! I talk a bunch about how uneven the distribution of values is.

John Carmack Ooh I made some visuals of the differences in precision of different floating point formats recently for a post on quantisation! I talk a bunch about how uneven the distribution of values is.

21,916 次观看

We released our new homepage redesign last week and after the release I got given some time to bring one of our diagrams to life. I'll be doing more of these over time <3

We released our new homepage redesign last week and after the release I got given some time to bring one of our diagrams to life. I'll be doing more of these over time <3

39,879 次观看

✨ New samwho visual essay o'clock! ✨ Reservoir sampling is one of my favourite algorithms. It allows you to sample from a set without knowing the size of that set. I assume no prior knowledge, and use no math notation. Just beautiful visuals. Let me know what you think! ❤️

✨ New samwho visual essay o'clock! ✨ Reservoir sampling is one of my favourite algorithms. It allows you to sample from a set without knowing the size of that set. I assume no prior knowledge, and use no math notation. Just beautiful visuals. Let me know what you think! ❤️

24,073 次观看

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

I think this is the best post I've ever made.

I think this is the best post I've ever made.

622,832 次观看 • 2 个月前

What if GitHub made you take a quiz about your PR before requesting reviews, to make sure you know what's in it? And if you don't...

What if GitHub made you take a quiz about your PR before requesting reviews, to make sure you know what's in it? And if you don't...

264,475 次观看 • 5 个月前

I downloaded something like 300GB of open models and wrote a bunch of map-reduce style processing scripts to make this graph. It's plotting the distribution of weight values across a variety of popular open models, to show that models are almost entirely made up of small floats.

I downloaded something like 300GB of open models and wrote a bunch of map-reduce style processing scripts to make this graph. It's plotting the distribution of weight values across a variety of popular open models, to show that models are almost entirely made up of small floats.

58,141 次观看 • 3 个月前

✨ Big O ✨ Let me take you on a visual introduction to what big O notation is in my new blog post: With big O notation you can better understand how algorithms will perform, finding orders of magnitude improvements with very simple changes to your code

✨ Big O ✨ Let me take you on a visual introduction to what big O notation is in my new blog post: With big O notation you can better understand how algorithms will perform, finding orders of magnitude improvements with very simple changes to your code

79,297 次观看 • 9 个月前

I wrote a lil' tool that extracts the attention matrices out of open models and creates this typing visual, with each token's opacity changing according to its average attention score as the prompt progresses. Dimmer words are considered less important to the model.

I wrote a lil' tool that extracts the attention matrices out of open models and creates this typing visual, with each token's opacity changing according to its average attention score as the prompt progresses. Dimmer words are considered less important to the model.

34,361 次观看 • 3 个月前

What does it mean for something to be Turing complete? I answer this question with a series of interactive Turing machine simulations! Play, pause, step forwards and backwards, and even write your own Turing machine programs in my latest blog post.

What does it mean for something to be Turing complete? I answer this question with a series of interactive Turing machine simulations! Play, pause, step forwards and backwards, and even write your own Turing machine programs in my latest blog post.

67,016 次观看 • 1 年前

I've been hacking away in the evenings on a little piece of JS you can drop into any page and let someone add comments. State is stored in the URL, and the plan is for me to use this to get feedback on my posts. I give them a URL, they send it back. No server, no fuss.

I've been hacking away in the evenings on a little piece of JS you can drop into any page and let someone add comments. State is stored in the URL, and the plan is for me to use this to get feedback on my posts. I give them a URL, they send it back. No server, no fuss.

22,962 次观看 • 11 个月前

没有更多内容可加载